Skip to content

Pull requests: NVIDIA/TensorRT-Model-Optimizer

New pull request New
45 Open 282 Closed
45 Open 282 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add L2NormHook and use it in megatron.py
#599 opened Nov 22, 2025 by danielkorzekwa Loading…
1
[OMNIML-2244] enable fp8 and int8 ONNX export
#594 opened Nov 21, 2025 by ajrasane Loading…
3
[2/N] Added KDLoss based AutoQuantize
#592 opened Nov 20, 2025 by realAsma Loading…
3
Convert compressed-tensor int4 format to GPTQ int4 format
#590 opened Nov 20, 2025 by Edwardf0t1 Loading…
2
Yeyu/eagle embedding optional
#589 opened Nov 20, 2025 by yeyu-nvidia • Draft
2
[3/N] Support for save/restoring AutoQuantize sensitivity scores
#588 opened Nov 20, 2025 by realAsma Loading…
2
[1/N] Refactored AutoQuantizeSearcher to _AutoQuantizeBaseSearcher & AutoQuantizeGradientSearcher; seperated quant modules and score modules
#586 opened Nov 20, 2025 by realAsma Loading…
17
Yeyu/remove embedding from eagle
#585 opened Nov 20, 2025 by yeyu-nvidia • Draft
1
Add sewing kit and utilities used for pruning scoring - pruning scoring is self-contained now
#584 opened Nov 20, 2025 by danielkorzekwa Loading…
3
Product Rename: TensorRT Model Optimizer to Model Optimizer
#583 opened Nov 20, 2025 by kevalmorabia97 Loading…
1 of 2 tasks
1
support for newer checkpoints
#582 opened Nov 20, 2025 by binghanc • Draft
1
Added support to export for BF16 weight and amax for vLLM fakequant QAT
#579 opened Nov 19, 2025 by kinjalpatel27 Loading…
@kinjalpatel27
17
Bump TRT-LLM docker to 1.2.0rc2 (CUDA 13)
#578 opened Nov 19, 2025 by kevalmorabia97 Loading…
1 task
1
[OMNIML-2244] Implement the ONNX quantization exporter for INT4
#575 opened Nov 18, 2025 by ajrasane Loading…
@ajrasane
2
Feat: SGL backend for online SD training
#564 opened Nov 14, 2025 by h-guo18 Loading…
@h-guo18
7
Fix hf_quant_config with kv cache type
#557 opened Nov 14, 2025 by jenchen13 Loading…
4
GPTQ Lite implementation
#555 opened Nov 13, 2025 by sugunav14 Loading…
1 of 2 tasks
@sugunav14
8
Specdec Bench: vLLM reqid, SGL path, conc > 1 metric fix
#541 opened Nov 12, 2025 by IzzyPutterman Loading…
4
[OMNIML-2850] [3/n] Adds sparse attention calibration
#538 opened Nov 11, 2025 by kaix-nv Loading…
1
Optimize NVFP4 Triton kernel
#533 opened Nov 11, 2025 by mxinO Loading…
@mxinO
7
[OMNIML-2852] [2/n] Add Core Sparse Attention Infrastructure
#527 opened Nov 7, 2025 by kaix-nv Loading…
2
parallel eagle draft
#523 opened Nov 6, 2025 by yeyu-nvidia • Draft
2
[Bug #193] fix fp8 blockwise real quantization
#522 opened Nov 6, 2025 by meenchen Loading…
@meenchen
2
Support AWQ fake quant for vLLM MoE models
#521 opened Nov 6, 2025 by meenchen • Draft
@meenchen
1
[Draft] [5526696] Add kv cache quantization support for onnx quantization
#486 opened Oct 31, 2025 by zhanghaoc Loading…
@zhanghaoc
19
ProTip! no:milestone will show everything without a milestone.