Skip to content

Pull requests: NVIDIA/TensorRT-Model-Optimizer

New pull request New
50 Open 219 Closed
50 Open 219 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

[NVBUG: 5619158] Enfore high precision model dtype for diffusion trt
#526 opened Nov 7, 2025 by ajrasane Loading…
@ajrasane
4
[BUG FIX 5616904] Add transformers version restoration after PTQ for VILA
#525 opened Nov 7, 2025 by yueshen2016 Loading…
1
[5620660][ONNX] Remove toposort after quantization
#524 opened Nov 7, 2025 by gcunhase Loading…
1
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
1
Support AWQ fake quant for vLLM MoE models
#521 opened Nov 6, 2025 by meenchen • Draft
@meenchen
1
Update custom file name patterns when copy files and remove problematic parameters in export
#520 opened Nov 6, 2025 by Edwardf0t1 Loading…
1
[1/n] Reorganize sparsity module to separate weight and attention sparsity
#517 opened Nov 6, 2025 by kaix-nv Loading…
3
Update changelog to include SGLang/vLLM related updates
#516 opened Nov 6, 2025 by Edwardf0t1 Loading…
2
Fix BMM style MoE export in fp8_pc_pt recipe
#515 opened Nov 5, 2025 by Edwardf0t1 Loading…
2
Fix DQ1 output type error in DQ1->DQ2 for FP4 weights in NVFP4 model
#513 opened Nov 5, 2025 by vishalpandya1990 Loading…
2
Alit/moe dev2
#508 opened Nov 4, 2025 by JRD971000 • Draft
1
[5591945][ONNX] Fix 'nodes not sorted' failure
#507 opened Nov 4, 2025 by gcunhase Loading…
1
Add decilm modelling code
#505 opened Nov 4, 2025 by danielkorzekwa Loading…
16
[OMNIML-2917] handle lm_head and other un-quantized modules correctly
#504 opened Nov 4, 2025 by shengliangxu Loading…
4
PyTorch geometric quantization support
#494 opened Nov 3, 2025 by i-riyad Loading…
9
Compress tutorial (PoC)
#492 opened Nov 3, 2025 by danielkorzekwa Loading…
3
fix qdq utils issues and remove global cast replacements
#489 opened Oct 31, 2025 by nvluxiaoz Loading…
7
Update benchmarking for diffusers
#487 opened Oct 31, 2025 by ajrasane Loading…
@ajrasane
2
[Draft] [5526696] Add kv cache quantization support for onnx quantization
#486 opened Oct 31, 2025 by zhanghaoc Loading…
@zhanghaoc
16
Fix/Improve vllm PTQ and Support multi-node with ray
#484 opened Oct 30, 2025 by mxinO Loading…
@mxinO
3
Yeyu/set block
#480 opened Oct 28, 2025 by yeyu-nvidia • Draft
1
feat: add onnxslim support
#478 opened Oct 28, 2025 by inisis Loading…
6
Add MoE (e.g. Qwen3-30B-A3B, Mamba hybrid) pruning support in Minitron
#467 opened Oct 27, 2025 by JRD971000 Loading…
@JRD971000
11
Feat: Eagle3 HF Online - support nemotron models
#463 opened Oct 25, 2025 by h-guo18 Loading…
@h-guo18
22
ProTip! Mix and match filters to narrow down what you’re looking for.