### What does this PR do?
Type of change: New feature <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
<!-- Details about the change. -->
By default, FP8 KV cache quantization in hf_ptq.py now uses a constant
scale of 1.0 (amax=448.0) without a data-driven calibration pass. No KV
scales are written to the exported checkpoint — inference engines
(TRT-LLM, vLLM) use scale=1.0 when no scale is
present, so this is lossless. Pass --calibrate_kv_cache to opt into
data-driven per-tensor KV scale calibration (previous default behavior).
To support this cleanly in the quantization stack, a constant_amax field
is added to QuantizerAttributeConfig. Quantizers configured with
constant_amax skip calibration entirely (no forward pass needed), use
the fixed amax during fake-quant, and produce no
_amax buffer in the state dict.
### Usage
```python
# Quantize with default constant KV scale (no calibration pass for KV)
python hf_ptq.py --model ... --qformat fp8 --kv_cache_qformat fp8
# Opt into data-driven KV calibration
python hf_ptq.py --model ... --qformat fp8 --kv_cache_qformat fp8 --calibrate_kv_cache
# Use constant_amax in a custom quant config
quant_cfg = {
"quant_cfg": {
"*[kv]_bmm_quantizer": {"num_bits": (4, 3), "enable": True, "constant_amax": 448.0},
},
"algorithm": "max",
}
model = mtq.quantize(model, quant_cfg, forward_loop=calibrate_loop)
```
### Testing
<!-- Mention how have you tested your change if applicable. -->
- All 8 existing GPU HF export tests pass
(tests/gpu/torch/export/test_unified_hf_export_and_check_safetensors.py)
- Two new CPU unit tests added to TensorQuantizerTester:
test_constant_amax and test_constant_amax_skips_calibration
### 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 (`git commit -s -S`).
Make sure you read and follow the [Security Best
Practices](https://github.com/NVIDIA/Model-Optimizer/blob/main/SECURITY.md#security-coding-practices-for-contributors)
(e.g. avoiding hardcoded `trust_remote_code=True`, `torch.load(...,
weights_only=False)`, `pickle`, etc.).
- Is this change backward compatible?: ✅ (--calibrate_kv_cache flag
defaults to False; existing scripts without the flag now skip KV
calibration)
- If you copied code from any other sources or added a new PIP
dependency, did you follow guidance in CONTRIBUTING.md: N/A
- Did you write any new necessary tests?: ✅
- Did you update Changelog?: ✅
### Additional Information
<!-- E.g. related issue. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* New CLI flag --calibrate_kv_cache to optionally enable data-driven KV
cache calibration; default uses a fixed KV scale and omits KV scales
from exported checkpoints.
* Added constant_amax option to set fixed quantizer scales and skip
dynamic calibration for configured quantizers.
* **Bug Fixes**
* Removed forced flooring/clamp of KV cache scales; out-of-range
activations now emit a shorter warning.
* **Tests**
* Added tests for constant_amax behavior and calibration interaction.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: weimingc <17592131+meenchen@users.noreply.github.com>
## What does this PR do?
new feature
**Overview:**
Enable mix hidden_states in eagle3 training. Deprecate eagle1
## Usage
Add --mix_hidden_states True to launch_train.sh
```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 --mix_hidden_states option to enable optional hidden-state
mixing during training.
* Added eagle_ttt_steps setting to control speculative multi-step
iterations.
* **Chores**
* Consolidated speculative decoding to EAGLE3 only; legacy Medusa/EAGLE1
paths removed.
* Unified configuration handling so models and plugins accept a single
config object.
* **Tests**
* Updated and expanded tests for hidden-state mixing and EAGLE3-only
scenarios.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Ye Yu <yeyu@nvidia.com>
`cuda-python` has mixed license and needs EStaff approval for usage. And
till 0.42, it was only used in
`examples/diffusers/cache_diffusion/pipeline` which has not been updated
in 9 months and not used anymore hence removing.
Also cherry-picked to `release/0.42.0` branch:
https://github.com/NVIDIA/Model-Optimizer/pull/984
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Chores**
* Removed TensorRT/ONNX deployment and inference tooling, related model
export/configuration, and runtime helpers from the cache-optimized
diffusion examples; removed the cuda-python example dependency.
* **Tests**
* Removed the example benchmarking script and its associated benchmark
test.
* **Documentation**
* Strengthened dependency-review, security, and PR guidance; updated PR
template and contributing documentation.
<!-- 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 tests
**Overview:**
Add new deployment tests for newly added checkpoints on HF
## Usage
pytest test_deploy.py --run-release
```python
None
```
## Testing
None
## 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
- **Did you add or update any necessary documentation?**: No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
No
## Additional Information
N/A
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added support for new model deployments: Qwen3 variants (480B, 235B,
397B), Kimi K2.5, and additional Mixtral configurations.
* **Improvements**
* Expanded backend support for select models, including TensorRT-LLM
integration for Nemotron models.
* **Chores**
* Renamed environment variable from MODELOPT_LOCAL_MODEL_ROOT to
MODELOPT_LOCAL_EAGLE_MODEL for improved clarity.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: noeyy-mino <174223378+noeyy-mino@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:**
Main changes:
- Refactored speculative decoding export logics into `class
EagleExporter` to improve cohesion;
- Separated speculative decoding export entrance with quantization
export (`export_hf_checkpoint()`) due to their fundamental differences:
- Quantization export base model's state_dict and config, while
speculative decoding only export drafter's.
- Most of the model-specific logics of quantization export (e.g.
diffusers, vlms) are not needed for speculative decoding export.
- Quantization export produce different format than speculative decoding
checkpoint. (The former produce tokenizer config, generation config,
e.t.c, while the later does not need. )
## Usage
<!-- You can potentially add a usage example below. -->
To export an regular bf16 eagle checkpoint without quantization, the
commands are the same:
```python
python scripts/export_hf_checkpoint.py --model_path <x> --export_path <x>
```
To run PTQ on online-trained eagle checkpoint and export it:
```python
python hf_ptq.py --pyt_ckpt_path <x> --qformat fp8 --export_path <x>
```
The above two commands will produce drafter ckpt for deployment, in the
same foramt.
## Testing
<!-- Mention how have you tested your change if applicable. -->
Tested setting:
- Base model: llama3.1-8b
- Algorithms: eagle
- Export path tested:
- (Unquantized online ckpt) `python scripts/export_hf_checkpoint.py
--model_path <x> --export_path <x>`
- (PTQ) export `python hf_ptq.py --pyt_ckpt_path <x> --qformat fp8
--export_path <x>`
- Tested deployment on vllm. Got normal AR.
## 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 export functionality for speculative decoding-optimized models
* Support for multiple speculative decoding architectures with
pre-configured deployment templates
* Enhanced model export detection and automatic routing for optimized
models
* **Tests**
* Updated export validation tests for speculative decoding models
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
### What does this PR do?
Type of change: Test infra improvement <!-- Use one of the following:
Bug fix, new feature, new example, new tests, documentation. -->
* Instead of spawning multiprocesses per test case (adds ~10s overhead x
150 tests), we spawn once per file (gpu_megatron) or session (gpu) to
make the tests much much faster
* Remove some unused / unnecessary tests
* Fix and enable Minitron NAS test on Hybrid models for Mcore 0.16
Test time (`pytest tests/<test_type>`) on 2x RTXPro 6000 Blackwell:
https://github.com/NVIDIA/Model-Optimizer/actions/runs/22625069275
| | gpu | gpu_megatron |
|------------|-----|--------------|
| **Before** | 27m | 40m |
| **After** | 16m | 19m |
Full PR-merge CI/CD now only takes ~45mins
### Testing
<!-- Mention how have you tested your change if applicable. -->
Tested on 1,2,4,8 GPU setup
### 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 (`git commit -s -S`).
Make sure you read and follow the [Security Best
Practices](https://github.com/NVIDIA/Model-Optimizer/blob/main/SECURITY.md#security-coding-practices-for-contributors)
(e.g. avoiding hardcoded `trust_remote_code=True`, using
`torch.load(..., weights_only=True)`, avoiding `pickle`, etc.).
- Is this change backward compatible?: ✅ <!--- If ❌, explain why. -->
- If you copied code from any other source, did you follow IP policy in
[CONTRIBUTING.md](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md#-copying-code-from-other-sources)?:
N/A <!--- Mandatory -->
- Did you write any new necessary tests?: ✅ <!--- Mandatory for new
features or examples. -->
- Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?:
N/A <!--- Only for new features, API changes, critical bug fixes or
backward incompatible changes. -->
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Chores**
* Reworked GPU test infra to use a persistent distributed worker pool
with improved per-worker teardown, aggregated error reporting,
Megatron-specific cleanup, reduced GPU CI timeouts, and a small
build-system dependency change.
* **Tests**
* Converted many multi-process GPU tests to a fixture-driven distributed
runner, updating test entry points and orchestration while preserving
test logic; adjusted imports and conditional guards for several GPU
tests.
<!-- 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 tests, Bug fix <!-- Use one of the following:
Bug fix, new feature, new example, new tests, documentation. -->
**Overview:**
- **Fixed the INT8 config issue**
- **Add HF checkpoint export test coverage**
1. The `--hf-ckpt-dir` export path had zero test coverage. This MR adds
tests at two levels:
2. Unit tests (tests/unit/torch/export/test_export_diffusers.py):
- Extended test_export_diffusers_real_quantized to parametrize over
INT8, INT8 SmoothQuant, FP8, and FP4 configs
- (previously only FP8). This gives 3 models x 4 configs = 12 test
cases.
3. GPU integration tests
(tests/gpu/torch/export/test_export_diffusers_hf_ckpt.py)
- New file testing the full quantize.py --hf-ckpt-dir pipeline via
subprocess with 4 combos:
- SDXL INT8 smoothquant min-mean (the exact scenario that triggered the
bug)
- Flux INT8 smoothquant min-mean
- SDXL FP8
- Flux FP4
## 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?**:No <!--- 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/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
* **Tests**
* Added test coverage for exporting Diffusers models with Hugging Face
checkpoints across multiple quantization formats (INT8, FP8, FP4)
* Extended quantization export testing to validate multiple
configuration scenarios
* **Chores**
* Refined INT8 quantization configuration with improved calibrator
support for convolution layers
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Jingyu Xin <jingyux@nvidia.com>
## What does this PR do?
**Type of change:**
New example
**Overview:**
Modify launch_train.sh script to enable multi-node training.
Provide a slurm template script.
## Usage
Add required fields in slurm.sh.
Then use the command below to submit multi-node job:
```bash
bash slurm.sh
```
## 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 multi-node training support with new configuration options for
distributed setups.
* Introduced Slurm batch script for streamlined job submission to
cluster environments.
* **Improvements**
* Enhanced GPU resource management for multi-GPU and distributed
training configurations.
* Updated speculative decoding model support and validation handling.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
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. -->
Bug fix
**Overview:** ?
Fix the example test.
## 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
* **Tests**
* Removed a sparse attention test variant to streamline test coverage.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Signed-off-by: Kai Xu <kaix@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:**
Patch transformers 5.x parameter loading to preserve original
`requires_grad` settings.
In transformers v5.x, loading a checkpoint forcibly sets parameters'
requires_grad,
which unintentionally unfreeze frozen parameters (e.g. Base model in
eagle training).
This leads to optimizer initialization error since the restored
optimizer expected more parameter than the checkpoint.
This monkey-patch restores the original`requires_grad` after loading
parameters.
Reference:
https://github.com/huggingface/transformers/blob/v5.0.0.rc1-release/src/transformers/core_model_loading.py#L640
## 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
* **Bug Fixes**
* Fixed model parameter loading in speculative decoding to properly
preserve gradient requirements for each parameter when using HuggingFace
Transformers 5.x, ensuring correct behavior during checkpoint resumption
and model initialization.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
## What does this PR do?
**Type of change:** Refactor <!-- Use one of the following: Bug fix, new
feature, new example, new tests, documentation. -->
**Overview:**
Jira ticket: https://jirasw.nvidia.com/browse/OMNIML-2955
Main changes :
- Consolidate Eagle data loading with @ChenhanYu 's implementation of
`transformers_dataset.py`
- Refactor: baked the following logics from `example/main.py` to
`modelopt/torch` for cleaner example entrance:
- default config selecting and merging with custom config
- tokenizer post-processor (chat template and pad_tok_id)
- d2t loading
- Implementation refactor: In HF workflow, reuse base modfel's input
hidden states as input_embedding, instead of calculating from input_ids.
This has two main benefits:
- Easier VLM support, which has various embedding processing logics.
- Training effieicy.
- Deprecating eagle1 from the example. It is still available by setting
custom config.
- Other minor fixes and readme updates.
## 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. -->
Tested that training curves after changes (both online&offline) is
identical with original branch:
<img width="1073" height="634" alt="image"
src="https://github.com/user-attachments/assets/abfd7bea-c82c-48a7-8181-68c5a9e4da8d"
/>
## 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 draft vocabulary cache support for EAGLE model training,
enabling runtime vocabulary customization via `--draft_vocab_cache`
parameter
* Introduced new data loading utilities with sharding, streaming, and
tokenization support for large-scale training
* Added optional `--log_steps` configuration to training launcher
* **Documentation**
* Updated EAGLE configuration guides with draft vocabulary cache setup
instructions and examples
* **Refactor**
* Restructured data pipeline for offline training with improved dataset
handling and batching
* Updated command-line arguments across training scripts (`--input-data`
replaces `--input-file`)
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: h-guo18 <67671475+h-guo18@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?
**Type of change:**
bug fix
**Overview:**
torch v2.10 changes the path for _SDPAMerger. will need to use the new
path for import
## 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
* **Chores**
* Updated internal import references to reflect organizational changes
in dependencies.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Ye Yu <yeyu@nvidia.com>
## What does this PR do?
**Type of change:** new tests
**Overview:** Add new test cases for the newly added checkpoints on
HuggingFace.
## Usage
pytest test_deploy.py --run-release
```python
None
```
## Testing
None
## 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
- **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/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
No
## Additional Information
None
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added support for NVFP4 model variants across multiple model families
(DeepSeek, Llama, Qwen, and others).
* **Improvements**
* Enhanced backend availability detection to automatically identify and
manage supported deployment backends at runtime.
* **Tests**
* Improved test infrastructure for better reproducibility and backend
compatibility handling.
<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: noeyy-mino <174223378+noeyy-mino@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:** New Feature <!-- Use one of the following: Bug fix,
new feature, new example, new tests, documentation. -->
**Overview:**
- Supported Context Parallel by patching torch ring attention;
- Require following libirary version for stable cp:
- torch2.8.0
- transformers5.0.0
- accelrate1.12.0
- Move to FSDP2
- Removed unused arguments in training script (`--multi_gpu`,
`fsdp_wrap_layer`)
- Bump CI container to `nvcr.io/nvidia/pytorch:25.08-py3`
## Usage
<!-- You can potentially add a usage example below. -->
```bash
./launch_train.sh --model $MODEL \
--output_dir $OUTPUT_DIR \
--data $DATA \
--num_epochs 0.1 \
--train_bs 1 \
--eagle_config eagle_config.json \
--training_seq_len 1024 \
--cp_size 2 #newly added
```
## Testing
- SDPA level correctness: tested TTT attention with/without CP, diff <
1%
```
=== Compare context-parallel (CP) outputs and grads with non-CP ===
Forward output comparison (CP vs Non-CP):
Absolute diff (adiff) cp_out vs out: 0.001953125
Relative diff (rdiff) cp_out vs out: 0.00182342529296875
WQ (query proj) grad comparison (CP vs Non-CP):
Absolute diff (adiff) cp_wq_grad vs wq_grad: 0.0078125
Relative diff (rdiff) cp_wq_grad vs wq_grad: 0.00347900390625
WK (key proj) grad comparison (CP vs Non-CP):
Absolute diff (adiff) cp_wk_grad vs wk_grad: 0.0078125
Relative diff (rdiff) cp_wk_grad vs wk_grad: 0.002471923828125
WV (value proj) grad comparison (CP vs Non-CP):
Absolute diff (adiff) cp_wv_grad vs wv_grad: 0.25
Relative diff (rdiff) cp_wv_grad vs wv_grad: 0.0069580078125
==============================================================
```
- E2E Training Acc
(Llama3.1-8B, Unsynthesized magpie)
<img width="911" height="630" alt="image"
src="https://github.com/user-attachments/assets/1ecacc7f-c720-494c-9c1b-b60e7ced7baa"
/>
- Peak Mem Reserved
(llama3.1-8B, 8xH100, train_length=4k)
| cp_size | max_memory_allocated(MB) |max_memory_reserved (MB) |
|----|--------------------------|--------------------------|
| 1 | 65040.20 |79018.00
| 2 | 50409.17 |73098.00
| 4 | 45120.92 |72052.00
| 8 | 38882.12 |66484.00
- Max Training Length test
(llama3.1-8B, H100)
| cp_size | 6k | 12k | 24k | 48k |
|--------------------|-----|-----|-----|-----|
| 1 | ✅ | OOM | OOM | OOM |
|2 | ✅ | ✅ | OOM | OOM |
| 4 | ✅ | ✅ | ✅ | OOM |
| 8 | ✅ | ✅ | ✅ | ✅ |
## 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 context parallelism (CP) and data parallelism shard size
configuration parameters to training arguments.
* **Enhancements**
* Improved TTT attention masking support for speculative decoding
workflows.
* Enhanced training launch script with improved parallelism
configuration handling.
* **Chores**
* Updated core dependencies: torch, transformers, accelerate, and wandb.
* Added FSDP configuration file for distributed training setup.
<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: h-guo18 <67671475+h-guo18@users.noreply.github.com>
## What does this PR do?
**Type of change:** Add TRT LLM/vLLM/SGLang functional test cases for
newly added checkpoints on HF
**Overview:**
1.Since the speculative draft model only supports loading from a local
path, we should set the MODELOPT_LOCAL_MODEL_ROOT environment variable.
If we don't set it, these test cases will be skipped.
2. Newly added checkpoints:
- nvidia/gpt-oss-120b-Eagle3-short-context
- nvidia/gpt-oss-120b-Eagle3-throughput
- nvidia/EAGLE3-NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
## Usage
```python
pytest tests/examples/llm_ptq/test_deploy.py --run-release
```
## Testing
Run release testing
## Before your PR is "*Ready for review*"
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
- **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/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
No
## Additional Information
N/A
---------
Signed-off-by: noeyy-mino <174223378+noeyy-mino@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 MLA Eagle support
- Add new argument "eagle_decoder_type" to switch between llama and
kimik2 eagle;
- Add patches to load from kimik2 model implementations dynamically;
- new default config for kimi k2;
- Refactor eagle export to support multilayer/multitype eagle export
concisely;
- Rename some modules for simplified export logic;
- Other minor improvements;
## 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. -->
- Tested that kimi k2 thinking works with eagle_type=kimik2:
<img width="1068" height="636" alt="image"
src="https://github.com/user-attachments/assets/5557ef87-c719-4fb1-be18-30435f6b3885"
/>
- Tested that llama 3.2 1b works with eagle_type=llama:
<img width="1066" height="634" alt="image"
src="https://github.com/user-attachments/assets/633c575c-cc79-43af-aed3-0378a303ebc7"
/>
## 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: h-guo18 <67671475+h-guo18@users.noreply.github.com>
Signed-off-by: yeyu-nvidia <yeyu@nvidia.com>
Co-authored-by: yeyu-nvidia <yeyu@nvidia.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:**
New Feature
**Overview:**
- Enable ONNX export for auto quantized models
- Update documentation and changelog
## Usage
<!-- You can potentially add a usage example below. -->
```
python torch_quant_to_onnx.py --quantize_mode=auto \
--onnx_save_path=./vit_base_patch16_224.nvfp4_fp8.onnx \
--calibration_data_size 64 \
--auto_quantization_formats NVFP4_AWQ_LITE_CFG FP8_DEFAULT_CFG \
--batch_size 128
```
## Testing
<!-- Mention how have you tested your change if applicable. -->
```
python evaluate.py --onnx_path=vit_base_patch16_224.nvfp4_fp8.onnx \
--model_name=vit_base_patch16_224 \
--results_path=./results.txt \
--batch_size 128
```
Accuracy results
```
The top1 accuracy of the model is 84.15%
The top5 accuracy of the model is 97.396%
```
Reference accuracy for fp16
```
The top1 accuracy of the model is 85.102%
The top5 accuracy of the model is 97.526%
```
## 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?**: No
- **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. -->
---------
Signed-off-by: ajrasane <131806219+ajrasane@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 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>
## What does this PR do?
**Type of change:** new tests
**Overview:** Add new checkpoints test cases.
## Usage
pytest test_deploy.py --run-release
```python
# Add a code snippet demonstrating how to use this
```
## Testing
N//A
## Before your PR is "*Ready for review*"
- **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?**: No
- **Did you update
[Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**:
No
## Additional Information
N/A
---------
Signed-off-by: noeyy-mino <174223378+noeyy-mino@users.noreply.github.com>
- [x] Product Rename: TensorRT Model Optimizer to Model Optimizer
(OMNIML-3033)
- [x] Mention in Latest News section with date on the date of merging
this PR (12/08)
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
Bump TRT-LLM docker from 1.1.0rc2.post2 (CUDA 12) to 1.2.0rc4 (CUDA 13)
## Testing
<!-- Mention how have you tested your change if applicable. -->
- [ ] 2-gpu tests for all examples: ?
## 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?**: No
- **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. -->
---------
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** Bug Fix
## Testing
<!-- Mention how have you tested your change if applicable. -->
- [x] Tests run locally in docker
- [x] Tests enabled in github per-PR CICD
---------
Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:** CICD infra improvement <!-- Use one of the
following: Bug fix, new feature, new example, new tests, documentation.
-->
- All example tests will now be run before PR can be merged
(onnx_ptq-bash still in gitlab as it needs internal scratch space
models. llm_eval / llm_autodeploy only run nightly to save per-PR gpu
resource)
- Users can also manually trigger specific test from
https://github.com/NVIDIA/TensorRT-Model-Optimizer/actions/workflows/example_tests.yml
- We no longer need to depend on internal gitlab infra for tests (except
nemo-megatron integration tests)
## Testing
<!-- Mention how have you tested your change if applicable. -->
- Tests run in PR and manually via workflow_dispatch
## 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?**: 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: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>
## What does this PR do?
**Type of change:**
Bug Fix
**Overview:**
- Added Int4QuantExporter to llm_export.py example
- Added E2E integration test for llm_export.py
## Testing
```
python llm_export.py --torch_dir=Qwen/Qwen2-0.5B-Instruct --dtype=fp8 --lm_head=fp16 --output_dir=./qwen2-0.5B-Instruct --calib_size=64 --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
- **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:** New feature, new tests; <!-- Use one of the
following: Bug fix, new feature, new example, new tests, documentation.
-->
**Overview:**
- Add conversion scripts for eagle3 llm-compressor style checkpoint
- Jira Ticket: https://jirasw.nvidia.com/browse/OMNIML-2866
- Add unit tests for `ar_validate.py`, `export_hf_checkpoint.py`, and
`convert_to_vllm_ckpt.py`.
## Usage
<!-- You can potentially add a usage example below. -->
```python
python scripts/convert_to_vllm_ckpt.py --input <eagle3 ckpt> --verifier <base model> --output <path>
```
## 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: h-guo18 <67671475+h-guo18@users.noreply.github.com>
## What does this PR do?
**Type of change:**
Example update
**Overview:**
- Updated the evaluation API to download `ImageNet` directly from HF
- Created a wrapper for the `ImageNet` dataset
- Added option to the evaluation API to pass custom transforms for
pre-processing images
- Removed `DeviceModel` compilation from the `evaluate()` API
- Removed `ImageNet` path argument
- Added option to evaluate accuracy in `torch_quant_to_onnx.py` example
## Usage
<!-- You can potentially add a usage example below. -->
```python
python evaluate.py \
--onnx_path=<path_to_onnx_model> \
--model_name=vit_base_patch16_224 \
--eval_data_size=10000 \
--results_path=./results.txt \
--engine_path=/tmp/tmp.engine
```
## Testing
Validated accuracy on the ViT model:
```
The top1 accuracy of the model is 84.83%
The top5 accuracy of the model is 97.37%
Inference latency of the model is 0.792418 ms
```
Accuracy comparison for the ViT model
| | Top-1 accuracy | Top-5 accuracy |
|------------------------------------------------------|----------------|----------------|
| Original model (FP32) | 85.102% | 97.526% |
| Auto Quantized (FP8 + NVFP4, 4.78 effective bits) | 84.726% | 97.434%
|
| MXFP8 Quantized | 85.02% | 97.53% |
| NVFP4 Quantized | 84.558% | 97.36% |
| INT4 Quantized | 84.23% | 97.22% |
## 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
- Added option to the evaluation API to pass custom transforms for
pre-processing images
- Removed `DeviceModel` compilation from the `evaluate()` API
- Removed `ImageNet` path argument
- **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:** new tests
**Overview:**
Add vLLM/SGLang/TRT LLM deployment tests for published checkpoints on
HF.
Add e2e test case for gpt-oss
## Usage
```python
# pytest test_deploy.py -k "vllm"
```
## Testing
## Before your PR is "*Ready for review*"
- **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?**: 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
## Additional Information
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Tests**
* Added ModelDeployer and ModelDeployerList test utilities with
COMMON_PROMPTS to run multi-backend deployment and inference scenarios.
* Introduced an end-to-end GPT-OSS QAT pipeline test (SFT → QAT → MXFP4
conversion) with optional deployment/benchmarking.
* Added a broad parametric LLM deployment test suite covering many
models/backends with readable test IDs.
* Added automatic Hugging Face cache cleanup after tests to keep runs
isolated.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: neoyy-mino <174223378+noeyy-mino@users.noreply.github.com>
Signed-off-by: noeyy-mino <174223378+noeyy-mino@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
## What does this PR do?
**Type of change:**
Minor code change
**Overview:**
- Delete backbone after Device Model creation
- Add assertion for torch compile
- Update dummy input generation function
## Testing
```
python diffusion_trt.py --model flux-dev --benchmark --skip-image
python diffusion_trt.py --model flux-dev --benchmark --skip-image --restore-from ./flux_dev_fp8_autodeploy_fake.pt
python diffusion_trt.py --model flux-dev --benchmark --skip-image --restore-from ./flux_dev_fp4_autodeploy_fake.pt
python diffusion_trt.py --model flux-dev --benchmark --skip-image --torch
python diffusion_trt.py --model flux-dev --benchmark --skip-image --restore-from ./flux_dev_fp8_autodeploy_fake.pt --torch
python diffusion_trt.py --model flux-dev --benchmark --skip-image --restore-from ./flux_dev_fp4_autodeploy_fake.pt --torch
python diffusion_trt.py --model flux-dev --benchmark --skip-image --torch --torch-compile
```
## 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?**: 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:** New example <!-- Use one of the following: Bug fix,
new feature, new example, new tests, documentation. -->
**Overview:** This PR provides an e2e example for fine-tuning a model
using QLoRA with DDP and exporting checkpoint for deployment using vllm.
1. This PR contains a temporary fix for loading best checkpoint in the
end for DDP which can be removed once we move to using get_peft_model()
2. The final base checkpoint is exported under output_dir/base_model
while the adapter weights are exported under output_dir
## Usage
<!-- You can potentially add a usage example below. -->
Refer to README.md changes
## Testing
<!-- Mention how have you tested your change if applicable. -->
Trainer
- [x] `./launch.sh --model meta-llama/Meta-Llama-3-8B --num_epochs 0.01
--lr 1e-3 --do_train True --output_dir test --quant_cfg FP8_DEFAULT_CFG
--compress True --lora True`
Export
- [x] `python export.py --pyt_ckpt_path test --export_dir test-fp8 `
Deployment
- [x] `vllm serve test-fp8/base_model --enable-lora --lora-modules
sql-lora=test-fp8 --port 8090 --tokenizer test-fp8`
- [x] e2e unit test
- [ ] Sanity check weights, dtypes of generated checkpoint
- [x] Test phi4
## 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/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 an export CLI/tool to produce HuggingFace-ready checkpoints from
LoRA/QLoRA-trained models, including optional restoration of quantizer
state.
* **Improvements**
* Export now respects a QLoRA mode, filters and strips adapter entries
appropriately, and only emits per-layer quantization when weight
quantization is enabled. Saves model state earlier after quantization
and tightens checks for exporting quantized weights.
* **Documentation**
* Expanded LLM QAT README with QLoRA export and deployment guidance.
* **Tests**
* Re-enabled a previously skipped QLoRA test.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Signed-off-by: Suguna Velury <178320438+sugunav14@users.noreply.github.com>
Signed-off-by: sugunav14 <178320438+sugunav14@users.noreply.github.com>
Co-authored-by: realAsma <86726418+realAsma@users.noreply.github.com>
Wei-Ming Chen