Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
131 Open 758 Closed
131 Open 758 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 SwinTransformer support for torch_onnx quantization workflow
#1235 opened Apr 10, 2026 by ajrasane Contributor Loading…
3 tasks
6
Fix test_collect_hidden_states: use synthetic short conversations
#1234 opened Apr 10, 2026 by yeyu-nvidia Contributor Loading…
2 tasks
5
vLLM fakequant: add recipe-based quantization support
#1233 opened Apr 10, 2026 by kinjalpatel27 Contributor Loading…
7
support Qwen3.5 quantization
#1230 opened Apr 10, 2026 by deepindeed2022 Loading…
4
[2/N] PTQ skill change for transformers 5.0
#1229 opened Apr 10, 2026 by mxinO Contributor Loading…
20
Pre-initialize torch._dynamo to prevent double-registration with peft torch.compile() call
#1228 opened Apr 9, 2026 by hychiang-git Contributor Loading…
9
[2/3] Implicit Gemm NVFP4
#1227 opened Apr 9, 2026 by jingyu-ml Contributor • Draft
4
Add LTX-2 third-party license notices for legal compliance cherry-pick After code freeze, cherry-pick into release branch for next rc. Only for bug fixes and doc updates
#1226 opened Apr 9, 2026 by kevalmorabia97 Collaborator Loading…
3 tasks
8
added gptq nvfp4 default recipe + docstring fix
#1224 opened Apr 9, 2026 by sugunav14 Contributor Loading…
1 task done
@sugunav14
8
GPTQ vector
#1223 opened Apr 9, 2026 by sugunav14 Contributor • Draft
4
consolidate mbridge distillation: merge distill_hf.py into distill.py
#1220 opened Apr 9, 2026 by j-rausch Contributor Loading…
16
Add Gemma4 MoE quantization support
#1219 opened Apr 9, 2026 by yueshen2016 Contributor Loading…
4 tasks done
6
Add WaterSIC for KV-cache quantization
#1217 opened Apr 9, 2026 by kaix-nv Contributor • Draft
5
Add TriAttention For KV Cache Compression
#1216 opened Apr 9, 2026 by kaix-nv Contributor • Draft
4
Add VLM base model support for auto_quantize in hf_ptq
#1214 opened Apr 9, 2026 by yueshen2016 Contributor Loading…
11
Add FP8 QKVO + NVFP4 MLP PTQ recipe
#1213 opened Apr 9, 2026 by yueshen2016 Contributor Loading…
13
add: DFlash block diffusion speculative decoding
#1211 opened Apr 8, 2026 by ChenhanYu Collaborator Loading…
@ChenhanYu
149
Add Z-Image (NextDiT/Lumina2) PTQ quantization support in diffusers example
#1205 opened Apr 8, 2026 by andrea-pilzer Loading…
2
Add support for postprocess exported model for block scale swizzling and support for different padding strategy
#1195 opened Apr 8, 2026 by ynankani Contributor Loading…
23
fix: handle accelerate CPU-offloaded models in FakeQuant export
#1194 opened Apr 8, 2026 by sungsooha Contributor Loading…
9
Simplify KDTrainer and enhance ModelOptHFTrainer
#1191 opened Apr 7, 2026 by realAsma Contributor Loading…
4 of 6 tasks
11
Add ModelOpt Triton attention kernels for WAN2.2 diffusion (sparse, skip-softmax, NVFP4)
#1190 opened Apr 7, 2026 by yeyu-nvidia Contributor Loading…
5 tasks
51
[chore]: weekly bump of uv.lock on main (2026-04-06)
#1180 opened Apr 6, 2026 by github-actions bot Loading…
3
GPTQ test
#1179 opened Apr 6, 2026 by sugunav14 Contributor • Draft
12
feat: parallelize fakequant export across GPUs via ThreadPoolExecutor
#1177 opened Apr 3, 2026 by sungsooha Contributor Loading…
26
ProTip! Follow long discussions with comments:>50.