-
Notifications
You must be signed in to change notification settings - Fork 550
Pull requests: NVIDIA/Model-Optimizer
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
docs(eval-skill): add NVFP4 model-card sampling reference
#2224
opened Aug 20, 2026 by
cjluo-nv
Collaborator
Loading…
Set NVFP4 MSE preset effective bits to 4.5
#2223
opened Aug 20, 2026 by
realAsma
Contributor
Loading…
fix(speculative): read rope_theta from rope_parameters first
#2221
opened Aug 20, 2026 by
h-guo18
Contributor
Loading…
Restructure recipes: split per-model_type recipes from model-hub checkpoint recipes
#2219
opened Aug 20, 2026 by
shengliangxu
Collaborator
Loading…
[Speculative Decoding] DFlash2 draft variant (sublayer convolution + candidate selector)
#2216
opened Aug 19, 2026 by
h-guo18
Contributor
Loading…
Harden Puzzletron orchestration state integrity
#2215
opened Aug 19, 2026 by
j-rausch
Contributor
Loading…
Group MLA q_a_proj/kv_a_proj_with_mqa projections in auto_quantize
#2213
opened Aug 18, 2026 by
joshua-hill
•
Draft
Add Kimi-K3 NVFP4 experts and FP8-PB attention recipe
#2206
opened Aug 17, 2026 by
Edwardf0t1
Contributor
Loading…
Updating Cosmos3 Nano DFlash recipe with optional fixes
#2205
opened Aug 17, 2026 by
adsridhar
Loading…
feat(quantization): fail fast when a quant config matches no weight quantizer
#2203
opened Aug 17, 2026 by
Edwardf0t1
Contributor
Loading…
feat(quantization): PTQ support for Step-3.7 MoE checkpoints
#2202
opened Aug 17, 2026 by
Edwardf0t1
Contributor
Loading…
Consolidate speculative-decoding agent skills into one stage/algorithm tree
#2201
opened Aug 17, 2026 by
yeyu-nvidia
Contributor
Loading…
[chore]: weekly bump of uv.lock on main (2026-08-17)
#2200
opened Aug 17, 2026 by
github-actions
Bot
Loading…
Gate evaluation Step 1 on the validated launcher version
#2198
opened Aug 14, 2026 by
Edwardf0t1
Contributor
Loading…
fix(specdec): generate all multimodal sources and pad VLM batches
#2195
opened Aug 14, 2026 by
skierat
Contributor
Loading…
Add offline SpinQuant/QuaRot rotation folding and learning (R1/R2)
#2187
opened Aug 13, 2026 by
BillRenCN
Loading…
feat(speculative): support Gemma-4-E4B as a streaming DFlash/DSpark target
#2186
opened Aug 13, 2026 by
h-guo18
Contributor
Loading…
fix: guard MoE branch when quantization_format is None
#2185
opened Aug 13, 2026 by
andrewwhitecdw
Loading…
Add Aumann-Shapley sensitivity scoring method to auto_quantize
#2183
opened Aug 12, 2026 by
joshua-hill
Loading…
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.