Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
204 Open 1,066 Closed
204 Open 1,066 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 non-deterministic T5 calibration NaN on multi-GPU
#1636 opened Jun 5, 2026 by kevalmorabia97 Collaborator Loading…
2
Add NVFP4 fakequant for attention BMM operands (prefill + decode)
#1635 opened Jun 5, 2026 by kaix-nv Contributor • Draft
2
Route decode-only skip-softmax through the decode kernel in vLLM
#1634 opened Jun 5, 2026 by kaix-nv Contributor • Draft
2
docs(skills): fix VLM PTQ ViT-quantization + AA eval judge/tool-call gaps
#1632 opened Jun 5, 2026 by Edwardf0t1 Contributor Loading…
6
fix(export): correct unified_export_megatron at EP > 1 and DP > 1
#1631 opened Jun 4, 2026 by yueshen2016 Contributor Loading…
3 of 4 tasks
9
[minor] fix for GLM4.7 mtp module in PTQ
#1630 opened Jun 4, 2026 by Fridah-nv Contributor Loading…
6
remove deprecated get_default_load_sharded_strategy
#1629 opened Jun 4, 2026 by dimapihtar Loading…
3
[6058841] Consistent types on If/Loop/Scan subgraphs during FP16/BF16 conversion
#1628 opened Jun 4, 2026 by ajrasane Contributor • Draft
10
[6058907] Fix ShapeInferenceError in ONNX int8+fp16 quantization of weakly-typed models
#1627 opened Jun 4, 2026 by ajrasane Contributor Loading…
5
docs(eval skill): vLLM backend env vars + SLURM HF-cache/cpu_partition guidance
#1625 opened Jun 4, 2026 by cjluo-nv Collaborator Loading…
7
Add efficient Triton decode attention kernel with fused skip-softmax …
#1624 opened Jun 3, 2026 by kaix-nv Contributor • Draft
4
Skip-Softmax calibration in vLLM
#1622 opened Jun 3, 2026 by kaix-nv Contributor • Draft
2
DFlash speculative decoding for MiniMax-M2.7 (FSDP2): auto mask-token, FSDP2 resume fixes, per-checkpoint draft export
#1621 opened Jun 3, 2026 by yeyu-nvidia Contributor Loading…
4
Add W4A16 NVFP4-MSE Qwen3.5 dense/MoE PTQ recipes
#1620 opened Jun 3, 2026 by cjluo-nv Collaborator Loading…
2
[OMNIML-4930] specdec_bench cell t1_d7 — Qwen/Qwen3.5-4B / MTP / vllm
#1619 opened Jun 3, 2026 by ChenhanYu Collaborator • Draft
3
[OMNIML-4929] specdec_bench cell t1_d3 — Qwen/Qwen3.5-4B / MTP / vllm
#1618 opened Jun 3, 2026 by ChenhanYu Collaborator • Draft
3
[OMNIML-4928] specdec_bench cell t0_d7 — Qwen/Qwen3.5-4B / MTP / vllm
#1617 opened Jun 3, 2026 by ChenhanYu Collaborator • Draft
2
[OMNIML-4927] specdec_bench cell t0_d3 — Qwen/Qwen3.5-4B / MTP / vllm
#1614 opened Jun 3, 2026 by ChenhanYu Collaborator • Draft
3
[OMNIML-4928] cell_t0_d7
#1613 opened Jun 2, 2026 by ChenhanYu Collaborator • Draft
2
[Feat]: Specdec Multinode Streaming
#1611 opened Jun 2, 2026 by h-guo18 Contributor Loading…
@h-guo18
26
[OMNIML-4886] specdec_bench cell t0_d3 — Qwen/Qwen3.5-4B / MTP / vllm
#1608 opened Jun 2, 2026 by ChenhanYu Collaborator • Draft
3
Fix torch import error to remove circular dependency & move Nemotron configs
#1606 opened Jun 2, 2026 by jenchen13 Contributor Loading…
8
[OMNIML-3994] Add SharedQuantState
#1605 opened Jun 2, 2026 by sychen52 Contributor Loading…
33
[OMNIML-4886] cell_t0_d3
#1603 opened Jun 2, 2026 by ChenhanYu Collaborator • Draft
2
Add NVFP4 + QAD to the Nemotron-3-Nano-30B-A3B tutorial
#1601 opened Jun 2, 2026 by kevalmorabia97 Collaborator • Draft
3
ProTip! no:milestone will show everything without a milestone.