Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
282 Open 1,571 Closed
282 Open 1,571 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

Speed up megatron_bridge example tests by ~6x on a single GPU cherry-pick-0.47.0 Upcoming release
#2296 opened Sep 1, 2026 by kevalmorabia97 Collaborator Loading…
36
Fix fsdp2_aware_weight_update masking setup errors with UnboundLocalError
#2295 opened Sep 1, 2026 by harshal-96 Loading…
2 of 4 tasks
1
5
feat(quantization): scoped calibration pipelines via algo_cfg [prototype]
#2292 opened Sep 1, 2026 by Fridah-nv Contributor • Draft
4
README: link Announcement Blogs and add AutoQuantize blog to Latest News
#2291 opened Aug 31, 2026 by realAsma Contributor Loading…
2
specdec: config_overrides for nested text_config checkpoints + load VLM-capable bases in merge_lora
#2289 opened Aug 31, 2026 by yeyu-nvidia Contributor Loading…
43
ar_validate: fail loudly when every sample fails
#2288 opened Aug 31, 2026 by yeyu-nvidia Contributor Loading…
17
[chore]: weekly bump of uv.lock on main (2026-08-31)
#2285 opened Aug 31, 2026 by github-actions Bot Loading…
1
Add WMSE weight scale search calibration
#2283 opened Aug 29, 2026 by realAsma Contributor • Draft
2
perf(speculative): speed up DFlash/DSpark drafter training 3.12x
#2279 opened Aug 28, 2026 by h-guo18 Contributor • Draft
2
Support quantized Qwen3-VL / Qwen3.5-VL (dense + MoE) export from Megatron-Bridge and verify exported checkpoints cherry-pick-0.47.0 Upcoming release
#2276 opened Aug 28, 2026 by kevalmorabia97 Collaborator Loading…
122
Compose GEMM and KV-cache AutoQuant workflows
#2273 opened Aug 27, 2026 by meenchen Contributor • Draft
2
Add standalone layer-wise KV-cache AutoQuant with forward KL
#2272 opened Aug 27, 2026 by meenchen Contributor • Draft
4
Gkarch/sync main 449a3992 puzzletron_v2 Related to feature/puzzletron_v2 branch
#2266 opened Aug 27, 2026 by grzegorz-k-karch Contributor Loading…
@grzegorz-k-karch
3
Add a Docker image for Puzzletron v2 workers puzzletron_v2 Related to feature/puzzletron_v2 branch
#2265 opened Aug 27, 2026 by j-rausch Contributor Loading…
10
Docs: Add WOA documentation cherry-pick-0.47.0 Upcoming release
#2264 opened Aug 27, 2026 by haoxiz-nvidia Contributor Loading…
@haoxiz-nvidia
12
Add TensorRT-RTX ABI EP support for ONNX quantization cherry-pick-0.47.0 Upcoming release
#2262 opened Aug 27, 2026 by haoxiz-nvidia Contributor Loading…
17
MTP support in per-layer fused export
#2259 opened Aug 26, 2026 by Fridah-nv Contributor • Draft
4
Docs: Add QAT and QAD guide [OMNIML-4859]
#2255 opened Aug 26, 2026 by jenchen13 Contributor Loading…
43
feat(export): add functional quantized weight export
#2251 opened Aug 26, 2026 by mxinO Contributor • Draft
3 of 4 tasks
4
fix: make huggingface_hub plugin import optional
#2250 opened Aug 26, 2026 by Y-T-G Contributor Loading…
7
fix(quantization): warn once when calibration runs with a KV cache
#2248 opened Aug 25, 2026 by Fridah-nv Contributor Loading…
52
specdec_bench: emit speculation_profile.json alongside acceptance metrics
#2247 opened Aug 25, 2026 by yeyu-nvidia Contributor Loading…
11
Add Aumann-Shapley AutoQuantize recipe integration
#2246 opened Aug 25, 2026 by joshua-hill Loading…
35
Add NVFP4/FP8 Q/K/P/V + 2:4 attention quantization for MLA (vLLM TRITON_MLA)
#2244 opened Aug 25, 2026 by kaix-nv Contributor • Draft
5
[ONNX] Add quantization sensitivity ranking + exclusion picker
#2240 opened Aug 24, 2026 by gcunhase Contributor Loading…
68
ProTip! Type g i on any issue or pull request to go back to the issue listing page.