## What does this PR do?
**Type of change:** New Feature
**Overview:**
This MR adds support to perform rotation for RHT in float32 if enabled
by quantization configuration. It also makes rotate argument in
quantization configuration of type bool (for backward compatibility) or
dict (added option for float32 rotation)
## Usage
```
python hf_ptq.py --pyt_ckpt_path meta-llama/Llama-3.2-3B-Instruct --qformat nvfp4 --export_fmt hf --dataset cnn_dailymail --export_path test --trust_remote_code --inference_pipeline_parallel 1 --batch_size 1 --calib_size 4 --kv_cache_qformat nvfp4_rotate
```
Updated `NVFP4_KV_ROTATE_CFG` locally with `"rotate": {"enable": True,
"rotate_fp32": True}`
```
...
model.layers.27.self_attn.k_bmm_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.3750 rotated (fp32) calibrator
=MaxCalibrator quant)
...
```
Updated `NVFP4_KV_ROTATE_CFG` locally with `"rotate": {"enable": True,
"rotate_fp32": False}`
```
model.layers.27.self_attn.k_bmm_quantizer TensorQuantizer((2, 1) bit fake block_sizes={-1: 16, 'type': 'dynamic', 'scale_bits': (4, 3)}, amax=8.3750 rotated calibrator=MaxCalibrator quant)
```
## Testing
Updated unit test in `tests/gpu/torch/quantization/test_hadamard.py`
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: No (updated existing test)
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added rotational input capability prior to quantization for RHT
(Rotated Hyperplane Transform).
* Introduced granular rotation configuration options enabling FP32
casting for improved numerical stability during transforms.
* **Tests**
* Expanded test coverage for rotation functionality with parameterized
FP32 casting scenarios.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>
## What does this PR do?
- Upgrade CICD test containers to latest
- Enable torch 2.10 testing in CICD
## Testing
<!-- Mention how have you tested your change if applicable. -->
CI/CD in this PR should pass
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added support for mixed-precision gradient handling with FSDP2.
* **Documentation**
* Updated Linux installation guide with CUDA 13.x support and cupy
dependency guidance.
* **Chores**
* Updated CI/CD workflows and test infrastructure to support PyTorch
2.10 and CUDA 13.
* Updated container image versions and test environment configurations.
* Updated TensorRT-LLM version requirements.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** new feature <!-- Use one of the following: Bug fix,
new feature, new example, new tests, documentation. -->
**Overview:**
Add a new calibration method for weight scale search. It considers
activation information by weighing scale candidates with local hessian
matrix. Initial experiments with Qwen3 8B NVFP4 shows improvements.
## Usage
<!-- You can potentially add a usage example below. -->
Use `NVFP4_W4A4_WEIGHT_LOCAL_HESSIAN_CFG` quantization config for
quantization and evaluation.
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added local Hessian-weighted MSE calibration pathway for NVFP4
per-block quantization with configurable amax search parameters and FP8
scale sweep support.
* **Tests**
* Added test coverage for the new local Hessian weight-only quantization
configuration.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
Signed-off-by: Frida Hou <201670829+Fridah-nv@users.noreply.github.com>
## What does this PR do?
**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
new feature
**Overview:** ?
- This PR adds the sparse attention calibration algorithm
- Chunked prefill to support long ctx_len
- Separated calibration for prefill and decode
## Usage
<!-- You can potentially add a usage example below. -->
```python
import modelopt.torch.sparsity.attention_sparsity as mtsa
# Apply sparse attention with calibration
model = mtsa.sparsify(model, config=SKIP_SOFTMAX_CALIB)
# Print summary - now shows actual thresholds
mtsa.print_sparse_attention_summary(model)
# Output:
# Method: flash_skip_softmax, Threshold: Dynamic (λ=437.395926)
# Or llm_eval integration
# HuggingFace sparse attention example
python examples/llm_sparsity/attention_sparsity/hf_sa.py \
--pyt_ckpt_path Qwen/Qwen3-4B \
--sparse_attn skip_softmax_calib
```
# The calibration method
## Calibration Algorithm
- Implemented the Inverse Power model: scale_factor = k / (1 -
sparsity)^p
- Fit model parameters (k, p) per phase using scipy.optimize.curve_fit
- At inference: threshold = k / (1 - target_sparsity)^p / seqlen
## Why Choosing the Inverse Power model?
The inverse power model better fits the relationship between sparsity
ratio and threshold_scale_factor.
<img width="2388" height="1082" alt="sparsity_model_analysis"
src="https://github.com/user-attachments/assets/4dfb45d4-8c16-4f15-a878-c8e08a9b6128"
/>
## Runtime Flexibility
- Target sparsity can be changed at inference time without recalibration
- Users can adjust module._sparse_method_instance.target_sparse_ratio
dynamically
- Threshold automatically adapts to sequence length
## Testing
<!-- Mention how have you tested your change if applicable. -->
The calibration results for `Qwen/Qwen3-30B-A3B-Thinking-2507` are shown
below and are mostly consistent with the ground-truth numbers collected
from the kernel side.
```
Prefill Calibration Results:
Model: scale_factor = k / (1 - sparsity)^p
Fitted k: 1003.3990
Fitted p: 1.2589
R-squared: 0.827549
Scale factors for different target sparsities:
Target Scale Factor
---------- ---------------
50% 2401.35
70% 4568.26
80% 7610.98
90% 18214.70
95% 43591.65
```
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
---------
Signed-off-by: Kai Xu <kaix@nvidia.com>
## What does this PR do?
[Short term]: Megatron based tests take a long time often resulting in
CICD timeout. Splitting megatron tests into a dedicated CICD job for
faster overall CI/CD run
[Mid/Long term]: Run all megatron gpu tests using `torchrun` instead of
`pytest` so all dist processes are already created and all individual
tests no longer need to setup and destroy their processes which adds a
lot of overhead per test
## Testing
<!-- Mention how have you tested your change if applicable. -->
- [x] 1-GPU CI/CD passing (on this PR)
- [x] 2-GPU CI/CD passing (on nightly run - manually triggered):
https://github.com/NVIDIA/Model-Optimizer/actions/runs/22000517688
---------
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
**Overview:** ?
## Usage
<!-- You can potentially add a usage example below. -->
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added NVFP4StaticQuantizer for improved 4-bit quantization with
enhanced precision control
* Introduced NVFP4MSECalibrator with flexible candidate generation for
calibration optimization
* **Improvements**
* Optimized GPU kernels for Hopper+ graphics cards with better
performance
* Extended Triton support to broader GPU compatibility
* Enhanced backward compatibility for restoring previously quantized
models
* **Tests**
* Added comprehensive test coverage for new quantizers and calibration
methods
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: realAsma <akuriparambi@nvidia.com>
## What does this PR do?
**Type of change:** New feature and bug fix
**Overview:**
Support Latent MOE and Repeated MTP for NemotronH models
- Enable latent MOE modules during megatron import/export
- Fix KV cache quantization export: remove old
`qkv_layer.output_quantizer` export & replace with proper
`k/v_bmm_quantizer` logic
- Improvements to EP amax sync
- Support repeated MTP import/export for NemotronH models (only BF16
export for MTP for now)
## Usage
<!-- You can potentially add a usage example below. -->
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added support for grouped MLP and self-attention scaling operations in
model export workflows
* Enhanced model parallel training capabilities with improved component
mapping
* Expanded quantization configuration handling with dynamic module
exclusion across distributed ranks
* Improved support for additional transformer engine components
* **Refactor**
* Reorganized internal export and import logic for improved
maintainability and specialist model architecture support
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: jenchen13 <jennifchen@nvidia.com>
Signed-off-by: Jennifer Chen <jennifchen@nvidia.com>
Signed-off-by: Jenny Chen <jennifchen@nvidia.com>
## What does this PR do?
**Type of change:** New feature <!-- Use one of the following: Bug fix,
new feature, new example, new tests, documentation. -->
**Overview:** Adds support for GPTQ algorithm. This PR implements a
modified version of the official GPTQ algorithm; the key difference is
that updated activations from each layer are not used for hessian
computation
## Usage
<!-- You can potentially add a usage example below. -->
Modify "algorithm" field in quant_cfg to "gptq_lite".
Note: Does not currently work with AWQ
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
- [x] Added unit tests to test helper functions + e2e flow
- [x] Perplexity and GPQA results
| Model | Qformat | Perplexity wikitext2 | GPQA |
|-------------|------------------------|------------------------|------|
| Qwen3-8B | INT4 weight only (modelopt + amax/7) no GPTQ | 10.75 | n/a
|
| Qwen3-8B | INT4 weight only (modelopt + amax/7) | **10.56** | 0.388 |
| Qwen3-8B | INT4 weight only + FP-Quant hessians + amax/7.5 | 10.25 |
**0.449** |
| Qwen3-8B | INT4 weight only (FP-Quant) | 10.24 | 0.46 |
| Qwen3-8B | NVFP4 static weight only | 10.25 | n/a |
| Qwen3-8B | NVFP4 static weight only no GPTQ | 10.25 | n/a |
| Qwen3-0.6B | NVFP4 static weight only | **22.75** | n/a |
| Qwen3-0.6B | NVFP4 dynamic weight only | 23.50 | n/a |
| Qwen3-0.6B | NVFP4 static weight only with FP-Quant hessians | 22.0 |
n/a |
| Qwen3-0.6B | NVFP4 static weight only no GPTQ | 24.25 | n/a |
Conclusions from results
- Perplexity remains the same or shows improvement with Modelopt
implementation. The magnitude of improvement is lesser in modelopt when
compared to FP-Quant
- GPQA shows no improvement with modelopt, but shows improvement with
FP-Quant
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes <!--- If No, explain why.
-->
- **Did you write any new necessary tests?**: Yes
- **Did you add or update any necessary documentation?**: No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
No <!--- Only for new features, API changes, critical bug fixes or bw
breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* GPTQ Lite quantization mode now available for efficient model
calibration
* GPU memory usage monitoring utility added
* Quantization configuration extended to support complex nested
structures and lists
* **Tests**
* Comprehensive test coverage added for GPTQ quantization workflows
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Suguna Velury <178320438+sugunav14@users.noreply.github.com>
## What does this PR do?
**Type of change:** new feature <!-- Use one of the following: Bug fix,
new feature, new example, new tests, documentation. -->
**Overview:** Add support for MXFP8 PTQ, enabling MXFP8 hardware
acceleration during inference on Blackwell GPUs.
## Usage
<!-- You can potentially add a usage example below. -->
```bash
export MODEL_PATH=/my_home/hf_models/nvidia/OpenMath2-Llama3.1-8B
export OUTPUT_PATH=/my_home/hf_models/nvidia/OpenMath2-Llama3.1-8B-MXFP8
mkdir -p $OUTPUT_PATH
python examples/llm_ptq/hf_ptq.py \
--export_fmt hf \
--dataset cnn_dailymail \
--pyt_ckpt_path $MODEL_PATH \
--export_path $OUTPUT_PATH \
--qformat mxfp8
```
The `hf_quant_config.json` of the output checkpoint:
```json
{
"producer": {
"name": "modelopt",
"version": "0.41.0.dev50+g7a796a875"
},
"quantization": {
"quant_algo": "MXFP8",
"kv_cache_quant_algo": "FP8",
"group_size": 32,
"exclude_modules": [
"lm_head"
]
}
}
```
And `config.json` (only the `quantization_config`):
```json
...
"quantization_config": {
"ignore": [
"lm_head"
],
"quant_algo": "MXFP8",
"kv_cache_scheme": {
"dynamic": false,
"num_bits": 8,
"type": "float"
},
"producer": {
"name": "modelopt",
"version": "0.41.0.dev50+g7a796a875"
},
"quant_method": "modelopt"
}
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
Used `hf_ptq.py` to quantize the model `nvidia/OpenMath2-Llama3.1-8B`
([available in
hugging-face](https://huggingface.co/nvidia/OpenMath2-Llama3.1-8B)), see
the example command above.
Checked that the generated MXFP8 checkpoint can be loaded with vLLM
(required changes in vLLM, not merged to main).
Added tests for `MXFP8QTensor` in
`tests/gpu/torch/quantization/test_qtensor_cuda.py`.
Added "mxfp8" in `tests/examples/llm_ptq/test_llm_ptq.py`
#### Support for Nemotron Models
Verify that Nemotron Nano V3 BF16 can be converted to MXFP8 using
`hf_ptq.py`:
https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added MXFP8 quantization format support with new scaling mechanisms
and quantization utilities.
* Updated configuration options, example scripts, and utilities to
recognize and process MXFP8 quantization workflows.
* Extended quantization export pipelines to handle MXFP8 quantized
models.
* **Tests**
* Expanded test coverage for MXFP8 quantization across various tensor
shapes, data types, and device configurations.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
## What does this PR do?
**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
new feature
**Overview:** ?
Adds fp8_scale_sweep mode to MSE calibrator for optimizing FP8-quantized
per-block scales in NVFP4 format.
## Usage
<!-- You can potentially add a usage example below. -->
Tested with this config
```python
NVFP4_WEIGHT_MSE_FP8_SWEEP_CFG = {
"quant_cfg": {
"*weight_quantizer": {
"num_bits": (2, 1),
"block_sizes": {-1: 16, "type": "static", "scale_bits": (4, 3)},
"axis": None,
"enable": True,
},
"*input_quantizer": {
"enable": False,
},
**_default_disabled_quantizer_cfg,
},
"algorithm": {
"method": "mse",
"fp8_scale_sweep": True,
},
}
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
**New Features**
- Added FP8 scale sweep option for quantization calibration, enabling
optimized scale value sweeping for NVFP4 per-block quantization.
- Introduced new NVFP4_WEIGHT_MSE_CFG configuration preset for improved
weight quantization workflows.
**Tests**
- Added test coverage validating FP8 scale sweep functionality and reset
behavior.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
## What does this PR do?
**Type of change:** new feature
**Overview:**
## Usage
```bash
cd ./examples/llm_ptq/
python hf_ptq.py \
--pyt_ckpt_path Qwen/Qwen3-4B \
--export_path /home/scratch.shiychen_coreai/quantized_models/Qwen3-4B-svdq \
--qformat nvfp4_awq_svdquant --kv_cache_qformat none --sparsity_fmt dense --calib_size 8
```
## Testing
exported checkpoint and loaded.
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added nvfp4_svdquant as a new quantization format option for LLM model
quantization workflows.
* **Limitations**
* Multi-GPU export configurations using tensor or pipeline parallelism
are not supported with nvfp4_svdquant quantization.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
## What does this PR do?
**Type of change:** New feature
- So far users we didnt have the NAS step from the Minitron paper so
users had to manually find a pruned architecture which fits that params
constraints and for that they have to tweak different combinations of
width and depth pruning
- This PR adds a simplified version of the NAS from paper. We first find
all candidate subnets that fit the user's params constraint and sort
them by parameter count.
- [Paper] Then we pick top K candidates, do distillation for ~2B tokens
and then select the one with best score (LM Loss / MMLU / other metric
we care about). Note that the one among these top K with highest params
is often not the best pruned model
- [ModelOpt] Then we pick top K candidates, and select the one with best
score (LM Loss / MMLU / other metric we care about). While doing KD
gives better indication on which one to pick, skipping it makes the
pruning much faster, much less compute intense, and finish everything in
single prune API instead of first exporting top K models, doing KD and
eval for all K models separately. We do print a Note in pruning step to
let users know this so they can do KD if they want slightly better
pruned model.
- Further full KD is still needed as usual
- We also restrict the search space choices (e.g. `hidden_size` multiple
of 256, `ffn_hidden_size` multiple of 512) to make the process
efficient. Users can configure this if they want to.
## Usage
<!-- You can potentially add a usage example below. -->
Pruning API is same as before:
```python
import modelopt.torch.prune as mtp
mtp.prune(
model,
mode="mcore_minitron",
constraints=constraints,
dummy_input=None, # Not used
config=config,
)
```
1. Manual Pruning (Existing):
```python
constraints = {"export_config": {"hidden_size: 3072", "ffn_hidden_size": 9216}}
config = {"forward_loop": forward_loop, "checkpoint": "/path/to/cache/pruning/scores.pth"}
mtp.prune(...)
```
2. NAS-based Auto Pruning (New):
```python
constraints = {"params": 6e9}. # prune to 6B params
config = {"forward_loop": forward_loop, "checkpoint": "/path/to/cache/pruning/scores.pth"}
# define the score_func to maximize (e.g MMLU, negative val loss, etc.)
from modelopt.torch.utils.plugins.megatron_mmlu import megatron_mmlu
def score_func(m):
return megatron_mmlu(m, tokenizer, percentage=0.05) # 5% sampled data for faster eval
config["score_func"] = score_func
# overwrite search space choices (showing defaults):
config["max_width_pruning"] = 0.4
config["max_depth_pruning"] = 0.2
config["hparams_to_skip"] = [] # can be used to disable pruning some hparams e.g. ["num_attention_heads"]
config["top_k"] = 10 # might be better to use 20 at the cost of longer time to prune
mtp.prune(...)
```
To configure search space (shows defaults):
```python
ss_config = mtp.mcore_minitron.get_mcore_minitron_config(
hidden_size_divisor=256,
ffn_hidden_size_divisor=512,
mamba_head_dim_divisor=8,
num_moe_experts_divisor=8,
num_layers_divisor=2,
)
mtp.prune(model, mode=[("mcore_minitron", ss_config)], ....)
```
## Testing
**Qwen3-8B -> 6B (~2 hours on 8xA5000)**
```python
0.4350 score -> {'num_layers': 34, 'hidden_size': 3328, 'ffn_hidden_size': 11264}
BEST 0.5705 score -> {'num_layers': 30, 'hidden_size': 3584, 'ffn_hidden_size': 11776}
0.4051 score -> {'num_layers': 36, 'hidden_size': 3840, 'ffn_hidden_size': 8192}
0.4593 score -> {'num_layers': 36, 'hidden_size': 3584, 'ffn_hidden_size': 9216}
0.2737 score -> {'num_layers': 36, 'hidden_size': 3072, 'ffn_hidden_size': 11776}
0.5556 score -> {'num_layers': 32, 'hidden_size': 3584, 'ffn_hidden_size': 10752}
0.3198 score -> {'num_layers': 28, 'hidden_size': 4096, 'ffn_hidden_size': 10240}
0.4119 score -> {'num_layers': 36, 'hidden_size': 4096, 'ffn_hidden_size': 7168}
0.3808 score -> {'num_layers': 36, 'hidden_size': 3328, 'ffn_hidden_size': 10240}
0.4783 score -> {'num_layers': 34, 'hidden_size': 3840, 'ffn_hidden_size': 8704}
```
**Nemotron-Nano-9B-v2 -> 7B (~2.5 hours on 8xA5000)**
```python
0.2629 score -> {'num_layers': 54, 'hidden_size': 4352, 'mamba_num_heads': 88, 'mamba_head_dim': 72, 'ffn_hidden_size': 15360}
0.2778 score -> {'num_layers': 50, 'hidden_size': 4480, 'mamba_num_heads': 128, 'mamba_head_dim': 56, 'ffn_hidden_size': 15680}
0.5041 score -> {'num_layers': 56, 'hidden_size': 4096, 'mamba_num_heads': 96, 'mamba_head_dim': 80, 'ffn_hidden_size': 14336}
BEST 0.6043 score -> {'num_layers': 48, 'hidden_size': 4352, 'mamba_num_heads': 120, 'mamba_head_dim': 80, 'ffn_hidden_size': 13824}
0.0772 score -> {'num_layers': 56, 'hidden_size': 4352, 'mamba_num_heads': 112, 'mamba_head_dim': 80, 'ffn_hidden_size': 10240}
0.3550 score -> {'num_layers': 50, 'hidden_size': 4480, 'mamba_num_heads': 112, 'mamba_head_dim': 64, 'ffn_hidden_size': 15680}
0.1016 score -> {'num_layers': 56, 'hidden_size': 4352, 'mamba_num_heads': 120, 'mamba_head_dim': 72, 'ffn_hidden_size': 10752}
0.5461 score -> {'num_layers': 46, 'hidden_size': 4480, 'mamba_num_heads': 128, 'mamba_head_dim': 72, 'ffn_hidden_size': 14848}
0.1992 score -> {'num_layers': 54, 'hidden_size': 4480, 'mamba_num_heads': 80, 'mamba_head_dim': 80, 'ffn_hidden_size': 14336}
0.5881 score -> {'num_layers': 48, 'hidden_size': 4480, 'mamba_num_heads': 112, 'mamba_head_dim': 80, 'ffn_hidden_size': 13824}
```
## Before your PR is "*Ready for review*"
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes <!--- If No, explain why.
-->
- **Did you write any new necessary tests?**: Yes
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes <!--- Only for new features, API changes, critical bug fixes or bw
breaking changes. -->
## Additional Information
OMNIML-3043
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added NAS-based Auto Pruning for Minitron models as an alternative to
manual pruning using parameter constraints
* Introduced parameter counting capabilities for architecture search
* **Documentation**
* Expanded pruning guides with detailed examples and workflows for both
manual and automatic pruning approaches
* Updated configuration documentation with granular divisor parameters
* **Improvements**
* Enhanced parameter counting support for models with dynamic or
mixture-of-experts modules
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
new feature
**Overview:** ?
Support static block-wise MSE for NVFP4 weight quantization.
Add a FP4 triton kernel that take in scales for each block. It also
quantizes the scales to FP8.
This PR does the following:
1. Enable static NVFP4 implementation, i.e. block scales for weights are
calculated during calibration and feed into fake quant kernels
2.Extend mse_calibrate to support static NVFP4 with block scales
searching by MSE and global scale set as MAX
3.Refinements: calibrate weight quantizers only once during MSE
calibration
## Usage
<!-- You can potentially add a usage example below. -->
Example config:
```python
NVFP4_WEIGHT_MSE_CFG = {
"quant_cfg": {
"*weight_quantizer": {
"num_bits": (2, 1),
"block_sizes": {-1: 16, "type": "static", "scale_bits": (4, 3)},
"axis": None,
"enable": True,
},
"*input_quantizer": {
"enable": False,
},
**_default_disabled_quantizer_cfg,
},
"algorithm": {
"method": "mse",
"step_size": 0.25,
"start_multiplier": 0.25,
"stop_multiplier": 2.0,
},
}
NVFP4_WEIGHT_ACT_MSE_CFG = {
"quant_cfg": {
"*weight_quantizer": {
"num_bits": (2, 1),
"block_sizes": {-1: 16, "type": "static", "scale_bits": (4, 3)},
"axis": None,
"enable": True,
},
"*input_quantizer": {
"num_bits": (2, 1),
"block_sizes": {-1: 16, "type": "dynamic", "scale_bits": (4, 3)},
"axis": None,
"enable": True,
},
**_default_disabled_quantizer_cfg,
},
"algorithm": {
"method": "mse",
"step_size": 0.25,
"start_multiplier": 0.25,
"stop_multiplier": 2.0,
},
}
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
---------
Signed-off-by: Fridah-nv <201670829+Fridah-nv@users.noreply.github.com>
## What does this PR do?
**Type of change:** New feature
**Overview:** Writes a new KLDiv Logits loss which only uses top-k vocab
values
## Usage
<!-- You can potentially add a usage example below. -->
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added Top-K logit filtering capability for knowledge distillation
workflows, enabling selective focus on high-probability tokens.
* **Improvements**
* Enhanced distributed tensor model-parallel operations with improved
awareness for gradient computation and reduction.
* Simplified legacy distributed operation constructs.
* **Tests**
* Introduced comprehensive test coverage for Megatron-based
distillation, validating both standard and Top-K filtering variants.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Asha Anoosheh <aanoosheh@nvidia.com>
## What does this PR do?
**Type of change:** Fix MCore KV Cache Quantization: Amax Device
Placement Bug; Code clean up; Distributed Sync of KVCache Quantizer
params; unittest expansion to hybrid models
**Overview:** Fixes bugs preventing MCore KV Cache quantization from
working during checkpoint restore.
### Bug Chain
**Bug 1:** `is_enabled = self.weight_quantizer.is_enabled if
hasattr(self, "weight_quantizer") else False`
No `weight_quantizer` for KV-cache-only quant → `is_enabled=False` →
metadata not saved → `modelopt_post_restore()` never called. *(Thanks to
@jenchen13 )*
**Bug 2:** After fixing Bug 1, `_amax` restored on CPU (via
`_reset_pytorch_state_from_metadata`). Fallback
`_calibrate_quantizers()` never called because `_amax` exists.
**Bug 3:** Even if called, `_calibrate_quantizers()` fails —
`core_attention` has no parameters → can't determine device/dtype.
### The Fix
1. Remove `is_enabled` check entirely — disabled modules may still need
metadata restore. Explicitly skip `output_layer` from extra state
callbacks (never quantized)
2. Set `dtype`/`device` on `core_attention` from parent Attention
module, `modelopt_post_restore()` calls `self.to(device, dtype)`
3. Remove dead `_calibrate_quantizers()` code (will bring back similar
logic for KV cache affine quantization)
### Previous Unit Test Was Wrong
`model_test` was `mtq.quantize()`'d, not `mto.restore()`'d. Never tested
actual restore path.
### Additional Fixes
- Amax sync across DP/TP for KV cache quantizers
- `flash_decode` auto-disabled
### Code Cleanup
Removed ~100 lines of dead code.
## Testing
1. MCore KV Cache QAD with Nano V3 + Context Parallel works
2. Unit tests: hybrid models, KV+GEMM configs, correct restore workflow,
backward pass validation
## Before your PR is "*Ready for review*"
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: Yes
- **Did you add or update any necessary documentation?**: No
- **Did you update Changelog?**: Yes
---------
Signed-off-by: realAsma <akuriparambi@nvidia.com>
Co-authored-by: Asma Thekkumpate <akuriparambi@cw-dfw-cs-001-vscode-02.cm.cluster>
## What does this PR do?
**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
**Overview:**
Add registry interface for custom quantization functional backend
## Usage
<!-- You can potentially add a usage example below. -->
see `tests/unit/torch/quantization/test_custom_backend.py` for usage
example.
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes
## Additional Information
<!-- E.g. related issue. -->
Signed-off-by: realAsma <akuriparambi@nvidia.com>
## What does this PR do?
- Code refactor, no logic change
- De-couple Minitron pruning importance estimator from Dynamic Module so
its easy to configure different importance logic for pruning
## Testing
<!-- Mention how have you tested your change if applicable. -->
- [x] CI/CD tests passing
- [x] Compare mmlu on pruned Qwen3-8B with previous and current
implementation
- [x] Compare mmlu on pruned Qwen3-30B-A3B with previous and current
implementation (lot of variance in results, some pruning configs better
some worse)
- [x] Compare mmlu on pruned Nemotron-Nano-v2-9B with previous and
current implementation
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
- Deprecate `num_query_groups` parameter pruning support in
`mcore_minitron` mode. This parameter pruning was not part of the paper
but added hacky support in the past which makes refactoring current
implementation a bit challenging hence removed its support.
- Besides, `num_query_groups` should be multiple of TP so its less
likely to be pruned.
- Users can still prune it if they want to by using ModelOpt 0.40.0 or
earlier
- Going forward, `num_query_groups` if passed in pruning `export_config`
should be same as original else raises an Exception.
- As a follow-up PR, I will de-couple DynamicModule with forward hooks /
hparam importance logic so its easy for users to change to different
scoring logic
## Testing
<!-- Mention how have you tested your change if applicable. -->
- [x] CI/CD Tests pass
- [x] Compare MMLU for pruning Qwen3-8B (nmm-sanbox) with previous and
current implementation
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: No. See reasoning above <!---
If No, explain why. -->
- **Did you write any new necessary tests?**: No
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes <!--- Only for new features, API changes, critical bug fixes or bw
breaking changes. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **Deprecations**
* num_query_groups parameter in Minitron pruning is deprecated. Use
ModelOpt 0.40.0 or earlier if pruning with this parameter is needed.
* **Documentation**
* Updated NAS search parameters documentation
* Refined pruning scope documentation for Transformer, MoE, and Mamba
models
* Updated example configurations and support matrix reflecting current
supported pruning parameters
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
new feature,
**Overview:**
This PR implements HF parallel draft by combining eagle and medusa. In
training, multiple medusa heads are added and trained together with
eagle. In inference, medusa heads are used to generate draft tokens
after all eagle tokens.
## Usage
Set parallel_draft_step>1 in eagle_config to enable parallel draft.
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
---------
Signed-off-by: Ye Yu <yeyu@nvidia.com>
## What does this PR do?
**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
New feature
**Overview:** ?
This PR provides a sparse attention support in ModelOpt for applying
attention sparsity through skip softmax method, enabling inference
speedups for LLMs.
Key Features:
- Skip softmax support
- Sparse attention config
- Extensible method registry for future sparse attention algorithms
- HuggingFace Transformers integration
- Phase-aware thresholds (separate prefill/decode)
[Design
doc](https://docs.google.com/document/d/1OgmTAKkoD4ZSWYXel-FeaQqmI5PtyNhQ4dEuhGiZAQQ/edit?tab=t.0#heading=h.dyp44woziy9x)
## Usage
<!-- You can potentially add a usage example below. -->
```python
import torch
import modelopt.torch.sparsity.attention_sparsity as mts
from transformers import AutoModelForCausalLM
# Load model (must use eager attention for softmax patching)
model = AutoModelForCausalLM.from_pretrained(
"meta-llama/Llama-2-7b-hf",
attn_implementation="eager", # Required!
torch_dtype=torch.bfloat16,
)
# Use pre-defined configuration
from modelopt.torch.sparsity.attention_sparsity import SKIP_SOFTMAX_DEFAULT
model = mts.sparsify(model, SKIP_SOFTMAX_DEFAULT)
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
### Unit Test
```bash
pytest tests/unit/torch/sparsity/attention_sparsity -v
pytest tests/gpu/torch/sparsity/attention_sparsity -v
pytest tests/examples/llm_sparsity/attention_sparsity -v
```
ALL PASSED.
### Accuracy
Benchmark: MMLU
Model: Qwen/Qwen3-4B
Cmd: python mmlu.py --model_name causal --model_path Qwen/Qwen3-4B
--sparse_cfg SKIP_SOFTMAX_DEFAULT
| | MMLU |
|----------------------|-------|
| BF16 | 69.96 |
| SKIP_SOFTMAX_DEFAULT | 69.86 |
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
---------
Signed-off-by: Kai Xu <kaix@nvidia.com>
iCo-authored-by: Asma Kuriparambil Thekkumpate <akuriparambi@nvidia.com>
## What does this PR do?
**Type of change:** New Feature
**Overview:**
This MR adds support for quantizing TE Ops in megatron, specifically
TERowParallelLinear, TEColumnParallelLinear and
TELayerNormColumnParallelLinear.
## Usage
It can be used by enabling TE spec in megatron
## Testing
Added unit tests for testing functionality
`test_homogeneous_sharded_state_dict_te_spec`
`test_convert_mcore_te_gpt_model`
`test_quantize_forward_backward`
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: Yes
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes
## Additional Information
<!-- E.g. related issue. -->
---------
Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>
## What does this PR do?
**Type of change:** Bug fix <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
**Overview:** Current context manager for FSDP2 aware weight update only
works for modules with bias=False. Updated the code to handle modules
with bias=True
## Usage
<!-- You can potentially add a usage example below. -->
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
`accelerate launch --config_file ./fsdp2.yaml --machine_rank=0
--num_machines=1 --num_processes=4 --main_process_ip=10.126.7.122
--main_process_port=6000
--fsdp_transformer_layer_cls_to_wrap=Qwen2DecoderLayer
./multinode_ptq.py --pyt_ckpt_path Qwen/Qwen2-7B-Instruct --qformat fp8
--kv_cache_qformat fp8 --batch_size 24 --calib_size 64 --export_path
B200-Qwen2-7B-Instruct-fp8-kvcache-fp8 --trust_remote_code`
`python /app/tensorrt_llm/examples/llm-api/quickstart_advanced.py
--model_dir B200-Qwen2-7B-Instruct-fp8-kvcache-fp8 --enable_attention_dp
--tp_size 1 --moe_ep_size 1 --kv_cache_fraction 0.6
--disable_kv_cache_reuse --max_batch_size 8 --max_num_tokens 1024
--trust_remote_code`
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes <!--- If No, explain why.
-->
- **Did you write any new necessary tests?**: N/A
- **Did you add or update any necessary documentation?**: N/A
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
? <!--- Only for new features, API changes, critical bug fixes or bw
breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
NVBug [5711927]
---------
Signed-off-by: Suguna Velury <178320438+sugunav14@users.noreply.github.com>
## What does this PR do?
**Type of change:**
New feature
**Overview:**
- Implemented the NVFP4QuantExporter
- Deprecated fp4qdq_to_2dq
- Updated tests
## Usage
```python
python torch_quant_to_onnx.py --quantize_mode=nvfp4 \
--onnx_save_path=vit_base_patch16_224.nvfp4.onnx \
--calibration_data_size 64 \
--batch_size 128
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
```
python evaluate.py --onnx_path=vit_base_patch16_224.nvfp4.onnx \
--model_name=vit_base_patch16_224 \
--results_path=./results.txt \
--batch_size 128
```
Results:
```
The top1 accuracy of the model is 84.39%
The top5 accuracy of the model is 97.312%
Inference latency of the model is 7.22412 ms
```
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: No
- Deprecated fp4qdq_to_2dq
- **Did you write any new necessary tests?**: No
- **Did you add or update any necessary documentation?**: No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
No <!--- Only for new features, API changes, critical bug fixes or bw
breaking changes. -->
Signed-off-by: ajrasane <131806219+ajrasane@users.noreply.github.com>
## What does this PR do?
**Type of change:** bug fix <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
**Overview:** instead of using amax, we should compute block_scale on
the fly
## Usage
<!-- You can potentially add a usage example below. -->
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
---------
Signed-off-by: weimingc <17592131+meenchen@users.noreply.github.com>
## What does this PR do?
**Type of change:** : Bug fix
**Overview:**
moved vLLM fakequant checkpoint export code to separate files:
1. for HF export -> modelopt.torch.export.plugins.vllm_fq_hf
2. for megatron export -> modelopt.torch.export.plugins.vllm_fq_megatron
## Usage
Refer to
[README.md](https://github.com/NVIDIA/TensorRT-Model-Optimizer/tree/096ee13ea62bbb0ce0a4e4128c439651374d6235/examples/vllm_serve#load-qatptq-model-and-serve-in-vllm-wip)
## Testing
- Tested HF approach by exporting bf16 model using QAT script and
running vllm server, verified amax values match
- Tested MCore approach by quantizing and exporting bf16 model using
quantize.sh and export.sh script and running vllm server, verified amax
values match
- Tested using unit tests in
`tests/gpu/torch/export/test_vllm_fq_hf_export.py` and
`tests/gpu/torch/export/test_vllm_fq_megatron_export.py`
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: NA
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
NA
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added dedicated export functions for vLLM fakequant checkpoint format,
supporting both HuggingFace and Megatron Core models.
* **Refactor**
* Simplified export API by removing conditional export flags for
cleaner, more predictable behavior.
* Reorganized export functionality into focused plugin modules for
improved maintainability.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Kinjal Patel <kinjalpravin@nvidia.com>
## What does this PR do?
**Type of change:**
Add onnxslim support
**Overview:** [Onnxslim](https://github.com/inisis/OnnxSlim) is under
active development and committed to long-time-support, it's easy to use
and is dependent on very few packages.
## Usage
```python
$ python -m modelopt.onnx.quantization --onnx_path=$MODEL_NAME.onnx --simplify
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
---------
Signed-off-by: inisis <desmond.yao@buaa.edu.cn>
Co-authored-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** Refator; Minor new feature
**Overview:** ?
1. Refactored AutoQuantizeSearcher to _AutoQuantizeBaseSearcher &
AutoQuantizeGradientSearcher - Prepares architecture for additional
search methods.
2. seperated quant modules and score modules - separate quantization
modules from scoring modules, enabling auto-quantization to measure
sensitivity at parent layers (e.g., MLP output for MoE experts) rather
than individual ops.
3. Also see https://github.com/NVIDIA/TensorRT-Model-Optimizer/pull/592
and https://github.com/NVIDIA/TensorRT-Model-Optimizer/pull/588
## Testing
See unittests; `tests/unit/torch/quantization/test_autoquant.py` and
`tests/unit/torch/quantization/plugins/test_huggingface.py`
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: Yes
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Not Required
## Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added support for score modules in quantization workflows.
* Added optional naming for quantization recipes.
* **Bug Fixes**
* Improved quantization grouping rules documentation with clearer
configuration examples.
* **Refactor**
* Renamed quantization module parameters for improved clarity.
* Enhanced quantization search architecture for better scalability.
<sub>✏️ Tip: You can customize this high-level summary in your review
settings.</sub>
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: realAsma <akuriparambi@nvidia.com>
Co-authored-by: Asma Kuriparambil Thekkumpate <akuriparambi@akuriparambi-mlt.client.nvidia.com>
## What does this PR do?
**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
**Overview:**
This PR and https://github.com/NVIDIA/TensorRT-LLM/pull/8698 enable
NVFP4 AWQ deployment for TRT-LLM. Specifically, this PR fuses
pre_quant_scale in following two cases:
* For MLP, pre_quant_scale of gate_proj layer is fused into up_proj's
weight, so we don't need an extra handle in downstream fused moe
kernels.
* For attention, we will try to fuse the pre_quant_scale of o_proj to
v_proj if their dimensions match, which means we will skip fusion for
MQA/GQA models.
## Usage
<!-- You can potentially add a usage example below. -->
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
unit test, e2e test for Qwen3 dense and moe models.
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
---------
Signed-off-by: weimingc <17592131+meenchen@users.noreply.github.com>
- CI tests for min transformers version (4.48) started failing since new
peft 1.18 was released yesterday blocking all new PRs from merging
- Transformers v5.0 is right around the corner so we should not
recommend too older version
- Set new minimum transformers to 4.53 instead of 4.48
- nemo:25.07+ and trtllm:1.0.0+ docker containers have transformers
4.53+
- ModelOpt will still likely work for transformers 4.48-4.52 for now but
going forward will not be tested in CICD
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** Improve existing feature <!-- Use one of the
following: Bug fix, new feature, new example, new tests, documentation.
-->
**Overview:** GPT-OSS model has Yarn RoPE which adds additional
nn.Embedding modules that need to be enabled in DynamicModule for
Minitron pruning
## Testing
<!-- Mention how have you tested your change if applicable. -->
- gpt-oss-20b pruned using M-LM pruning example and conf scripts.
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** New feature <!-- Use one of the following: Bug fix,
new feature, new example, new tests, documentation. -->
- Support pruning `num_moe_experts`, `moe_ffn_hidden_size`, and
`moe_shared_expert_intermediate_size` in `mcore_minitron` pruning
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes <!--- If No, explain why.
-->
- **Did you write any new necessary tests?**: Yes
- **Did you add or update any necessary documentation?**: Yes
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes <!--- Only for new features, API changes, critical bug fixes or bw
breaking changes. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
## Release Notes
* **New Features**
* Added Mixture of Experts (MoE) pruning support with new configurable
dimensions for expert count and intermediate sizes
* Extended NAS architecture search capabilities to include MoE model
parameters
* **Documentation**
* Updated support matrix and pruning documentation for MoE-compatible
models
* Clarified available pruning dimensions and parameters for MoE
architectures
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
Co-authored-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** ? <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
**Overview:** ?
Reorganizes the `modelopt/torch/sparsity` module to prepare for adding
attention sparsity support. All existing weight sparsity functionality
(source code and tests) is moved into a dedicated `weight_sparsity`
subdirectory while maintaining full backward compatibility.
```
# These imports still work exactly as before
from modelopt.torch.sparsity import sparsify, magnitude_prune
from modelopt.torch.sparsity.mode import SparsityMode
```
## Usage
<!-- You can potentially add a usage example below. -->
```python
# Add a code snippet demonstrating how to use this
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->
- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes/No <!--- If No, explain
why. -->
- **Did you write any new necessary tests?**: Yes/No
- **Did you add or update any necessary documentation?**: Yes/No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
Yes/No <!--- Only for new features, API changes, critical bug fixes or
bw breaking changes. -->
## Additional Information
<!-- E.g. related issue. -->
Signed-off-by: Kai Xu <kaix@nvidia.com>
kinjalpatel27