Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
131 Open 825 Closed
131 Open 825 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

fix: preserve q/k/v quantizer mapping in AST attention patching
#1307 opened Apr 21, 2026 by Brumbelow Loading…
4 tasks done
1
2
fix: validate modelopt state file structure on load
#1306 opened Apr 21, 2026 by Brumbelow Loading…
3 tasks done
1
4
Kinjal/fix vllm moe
#1305 opened Apr 21, 2026 by kinjalpatel27 Contributor • Draft
6
fix: disable nvidia-resiliency-ext when incompatible with container PyTorch
#1304 opened Apr 21, 2026 by ChenhanYu Collaborator • Draft
1 task done
4
Reorg the sparse/quant/common kernel dir
#1303 opened Apr 20, 2026 by jingyu-ml Contributor Loading…
6
[CI] Bump test containers to latest
#1299 opened Apr 20, 2026 by kevalmorabia97 Collaborator Loading…
7
[3/3][Refactor]: Extract HFSpecDecMixin for HF spec-decoding plugins
#1297 opened Apr 19, 2026 by h-guo18 Contributor • Draft
2
[1/3][Refactor]: File reorg; deprecate ParallelDraft
#1296 opened Apr 19, 2026 by h-guo18 Contributor Loading…
@h-guo18
16
[2/3][Feat]: Offline DFlash training
#1295 opened Apr 19, 2026 by h-guo18 Contributor • Draft
1 task done
@h-guo18
4
add gptq fused kernel
#1291 opened Apr 17, 2026 by sychen52 Contributor Loading…
35
Add FP8 MHA quantization support for HuggingFace ViT
#1289 opened Apr 17, 2026 by ajrasane Contributor Loading…
5 tasks
32
keep deploy cases and Eagle fixes for merge
#1287 opened Apr 17, 2026 by nvSiruiW Loading…
5
Update excluded modules for Qwen3.5 dense PTQ
#1284 opened Apr 17, 2026 by amukkara Loading…
2
Add qwen3 moe experts only test
#1274 opened Apr 16, 2026 by cjluo-nv Collaborator Loading…
12
SpecDec Bench: April Update
#1272 opened Apr 16, 2026 by IzzyPutterman Contributor Loading…
35
[Feat,Refactor]: Offline Dflash; Spec Mixin; Deprecate parallel draft;
#1271 opened Apr 16, 2026 by h-guo18 Contributor Loading…
@h-guo18
18
Skip Softmax diffusion export
#1269 opened Apr 15, 2026 by jingyu-ml Contributor Loading…
@jingyu-ml
11
Centralize 'trtexec' subprocess runs in ONNX into a single function
#1268 opened Apr 15, 2026 by gcunhase Contributor Loading…
10
Handle zero-amax per-channel activation scaling for MoE export
#1265 opened Apr 15, 2026 by AEON-7 Loading…
5
Fix non-scalar input amax in preprocess_linear_fusion for MoE export
#1264 opened Apr 15, 2026 by AEON-7 Loading…
2
Exclude small-k and small-n Matmul nodes from Int8 quantization
#1256 opened Apr 14, 2026 by nv-samcheng Contributor Loading…
7
Add EfficientViT support for torch_onnx quantization workflow
#1254 opened Apr 14, 2026 by ajrasane Contributor Loading…
3 tasks done
7
Add a general composable $import system for YAML configs, and use it to implement composable recipes
#1253 opened Apr 14, 2026 by shengliangxu Collaborator Loading…
32
fix(launcher): use afterany dependency for allow_to_fail pipelines
#1248 opened Apr 13, 2026 by yeyu-nvidia Contributor Loading…
3 tasks
3
Add LAQ (Learnable Amax Quantization) algorithm
#1247 opened Apr 13, 2026 by realAsma Contributor Loading…
4 tasks
2
ProTip! no:milestone will show everything without a milestone.