Keval Morabia 9e64f81a67 NAS export refactor + skip conversion on minitron restore (#424) ...

Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com>

2025-10-11 10:21:37 +00:00

..

chained_optimizations

Code quality improvements - typos, formatting, etc.

2025-09-02 19:58:33 +05:30

cnn_qat

Add llm_ptq PR test, Cleanup dependency installation in modelopt docker (#338)

2025-09-19 10:48:44 +05:30

deepseek

Push latest changes

2025-09-04 11:02:58 +05:30

diffusers

Deprecate ModelOpt custom docker and directly use TRT-LLM / PyTorch / TRT docker (#346)

2025-09-23 01:43:25 +05:30

gpt-oss

Deprecate TRTLLM-build in examples (#297)

2025-09-18 03:22:37 +05:30

llm_autodeploy

Deprecate ModelOpt custom docker and directly use TRT-LLM / PyTorch / TRT docker (#346)

2025-09-23 01:43:25 +05:30

llm_distill

Fix llm_distill example saving issue on new transformers w FSDP2 (#413)

2025-10-08 16:34:20 +00:00

llm_eval

Remove Qwen tokenizer modification (#390)

2025-10-04 17:41:08 +05:30

llm_ptq

Remove Qwen tokenizer modification (#390)

2025-10-04 17:41:08 +05:30

llm_qat

Deprecate ModelOpt custom docker and directly use TRT-LLM / PyTorch / TRT docker (#346)

2025-09-23 01:43:25 +05:30

llm_sparsity

Fix the fsdp cmd in llm_sparsity (#417)

2025-10-10 19:01:50 +00:00

megatron-lm

NAS export refactor + skip conversion on minitron restore (#424)

2025-10-11 10:21:37 +00:00

model_hub

Code quality improvements - typos, formatting, etc.

2025-09-02 19:58:33 +05:30

nemo_run

Sync amax & AWQ-Lite act_scale in context parallel/data parallel [OMNIML-2813] (#359)

2025-10-10 23:16:27 +00:00

onnx_ptq

[5256037] Automatically infer calibration shapes for per node calibration (#394)

2025-10-01 10:07:29 -07:00

pruning

Add minitron pruning and distillation guidelines in pruning readme (#419)

2025-10-10 10:06:25 +00:00

speculative_decoding

[Eagle Offline] multinode support for hidden states dumper (#422)

2025-10-10 15:58:22 -07:00

vllm_serve

[New feature] Support fakequant serve with latest vllm and generalize calib logic (#369)

2025-10-07 18:17:21 +00:00

vlm_ptq

[NVBUG: 5535437] Refactor engine_dir to checkpoint_dir in PTQ examples. (#365)

2025-09-25 12:07:06 -07:00

windows

Add command-line options in Windows' llm-ptq example for Gather nodes' INT4 ONNX quantization (#418)

2025-10-10 11:15:05 +05:30

benchmark.md

Code quality improvements - typos, formatting, etc.

2025-09-02 19:58:33 +05:30