Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
124 Open 742 Closed
124 Open 742 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: DFlash block diffusion speculative decoding
#1211 opened Apr 8, 2026 by ChenhanYu Loading…
27
Replace in-repo LLM ONNX export with TensorRT-Edge-LLM
#1210 opened Apr 8, 2026 by ajrasane Loading…
5
Upgrade ONNX from 1.19 to 1.21
#1207 opened Apr 8, 2026 by ajrasane Loading…
8
Consolidate lm-eval scripts: merge AnyModel auto-detection into lm_eval_hf.py
#1206 opened Apr 8, 2026 by j-rausch Loading…
9
Add Z-Image (NextDiT/Lumina2) PTQ quantization support in diffusers example
#1205 opened Apr 8, 2026 by andrea-pilzer Loading…
2
[1/N] Polish PTQ skills
#1198 opened Apr 8, 2026 by Edwardf0t1 Loading…
8
Add support for postprocess exported model for block scale swizzling and support for different padding strategy
#1195 opened Apr 8, 2026 by ynankani Loading…
11
fix: handle accelerate CPU-offloaded models in FakeQuant export
#1194 opened Apr 8, 2026 by sungsooha Loading…
9
Validate non-empty cfg when enabling quantizers in quant_cfg
#1192 opened Apr 7, 2026 by shengliangxu Loading…
5
Simplify KDTrainer and enhance ModelOptHFTrainer
#1191 opened Apr 7, 2026 by realAsma Loading…
4 of 6 tasks
2
Add ModelOpt Triton attention kernels for WAN2.2 diffusion (sparse, skip-softmax, NVFP4)
#1190 opened Apr 7, 2026 by yeyu-nvidia Loading…
5 tasks
51
Generic Fused MoE Quantization + Export for transformers 5.0+
#1187 opened Apr 7, 2026 by Edwardf0t1 Loading…
2 of 3 tasks
17
[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 • Draft
2
feat: parallelize fakequant export across GPUs via ThreadPoolExecutor
#1177 opened Apr 3, 2026 by sungsooha Loading…
26
[1/N] Refactor llm_qat example: YAML configs + ModelOptArgParser
#1172 opened Apr 2, 2026 by realAsma Loading…
3 of 4 tasks
18
[minor] add a general FP8ScaleSweepCalibrator and its registry
#1171 opened Apr 2, 2026 by Fridah-nv Loading…
@Fridah-nv
3
Refactor Qwen3.5 MoE quantization to use _QuantFunctionalMixin
#1170 opened Apr 2, 2026 by cjluo-nv Loading…
4 tasks
3
Add the Skip softmax for diffusion
#1166 opened Apr 2, 2026 by jingyu-ml Loading…
@jingyu-ml
24
recipes doc
#1165 opened Apr 2, 2026 by shengliangxu • Draft
4
[NVBug 6045859]Fix export support for Qwen3VL MoE experts
#1164 opened Apr 1, 2026 by shengliangxu Loading…
4
Added support for MoE for vllm >= 0.14.0rc1
#1162 opened Apr 1, 2026 by kinjalpatel27 Loading…
17
Fix[bug] ONNX models generated by llm_export.py are missing some i/o
#1157 opened Apr 1, 2026 by Ratheesh1104 Loading…
5
fix spelling errors
#1153 opened Apr 1, 2026 by noeyy-mino Loading…
4
Intermediate checkpointing for sequential calibration
#1152 opened Mar 31, 2026 by sugunav14 Loading…
14
ProTip! Add no:assignee to see everything that’s not assigned.