-
Notifications
You must be signed in to change notification settings - Fork 595
Pull requests: NVIDIA/Model-Optimizer
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix(quantization): correct the affine-quant bias config contract
#2422
opened Sep 12, 2026 by
sriharshapy
Loading…
Fix NF4 dequantize when the scales span more than one int8 group
#2421
opened Sep 12, 2026 by
rootkiller6788
Loading…
Fix AutoCast unknown dimension metadata
#2420
opened Sep 12, 2026 by
haoxiz-nvidia
Contributor
Loading…
Env: update onnxruntime and cuda flag
#2419
opened Sep 12, 2026 by
haoxiz-nvidia
Contributor
Loading…
[6466805] Add Dynamo ONNX export support for quantized models
#2418
opened Sep 12, 2026 by
ajrasane
Contributor
Loading…
docs: add Local Hessian NVFP4 weight-scale announcement blog
#2417
opened Sep 11, 2026 by
realAsma
Contributor
Loading…
[5612316][OMNIML-2983] Fix FP8 QDQ placement for delegated diffusion attention
#2416
opened Sep 11, 2026 by
ajrasane
Contributor
Loading…
[6721556] Fix mixed dtypes in NVFP4 FP16 ONNX export
#2415
opened Sep 11, 2026 by
ajrasane
Contributor
Loading…
Fix vLLM fakequant calibration for hybrid attention models
#2414
opened Sep 11, 2026 by
kinjalpatel27
Contributor
Loading…
Add end-to-end W4A4 NVFP4 + QAD tutorial for Qwen3.6-35B-A3B
cherry-pick-0.47.0
Upcoming release
#2411
opened Sep 11, 2026 by
kevalmorabia97
Collaborator
Loading…
fix(specdec): resolve the eagle aux-layer preset in the vLLM hidden-state dump
#2410
opened Sep 11, 2026 by
yeyu-nvidia
Contributor
Loading…
Noeyy/fix bug 6701777
cherry-pick-0.47.0
Upcoming release
#2402
opened Sep 11, 2026 by
noeyy-mino
Contributor
Loading…
Reuse a whole recipe via $import, deprecate recipe_type, and backfill the recipes behind NVIDIA's published checkpoints
#2376
opened Sep 11, 2026 by
shengliangxu
Collaborator
•
Draft
Audit missing labels before release cherry-picks
#2373
opened Sep 10, 2026 by
chadvoegele
Contributor
Loading…
Add Qwen 3.5 4B all-axis VLM campaign
puzzletron_v2
Related to feature/puzzletron_v2 branch
#2372
opened Sep 10, 2026 by
j-rausch
Contributor
Loading…
Invalidate sharded sparsity masks after updating the source mask
#2370
opened Sep 10, 2026 by
MrCapricornLiu
Loading…
Release cached activations when exporting distillation models
#2368
opened Sep 10, 2026 by
MrCapricornLiu
Loading…
Fix folding transposed GPT-OSS and Llama 4 expert weights
#2367
opened Sep 10, 2026 by
MrCapricornLiu
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.