Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
304 Open 1,736 Closed
304 Open 1,736 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

Require timeout and output-limit accounting in eval skills
#2499 opened Sep 22, 2026 by Edwardf0t1 Contributor Loading…
2
feat(distill): support padded vocabulary tails
#2498 opened Sep 22, 2026 by efegokdemir Loading…
1
4
Add GDN state/W QAT emulation and linear-attention references
#2497 opened Sep 22, 2026 by kaix-nv Contributor • Draft
4
specdec_bench: forward kv_cache_dtype to the vLLM engine
#2496 opened Sep 22, 2026 by yeyu-nvidia Contributor Loading…
7
Make kernels.common.attention independent of kernels.sparsity
#2495 opened Sep 22, 2026 by sychen52 Contributor • Draft
3
Fix GitLab authentication guidance for Enroot
#2493 opened Sep 21, 2026 by chadvoegele Contributor • Draft
3
Bound the stale-capture warning to once per capture and name its cause
#2492 opened Sep 21, 2026 by Edwardssss Loading…
1
2
Use math.fsum for StaticLossBalancer weight checks
#2491 opened Sep 21, 2026 by aniruddh-krovvidi Loading…
1
2
fix: use explicit head dim for Puzzletron KV cache
#2485 opened Sep 20, 2026 by devxMani Loading…
1
8
[Puzzletron] Fix KV-cache dimension calculation for models with custom head_dim (#2482)fix(puzzletron): respect explicit head_dim in KV-cache dimension calc…
#2484 opened Sep 20, 2026 by musi22 Loading…
2
fix(speculative): hold the DFlash draft's fp32 master weights in the optimizer
#2483 opened Sep 20, 2026 by h-guo18 Contributor Loading…
@h-guo18
18
docs(eval): align Terminal-Bench 2.1 / SWE-bench / MRCR with upstream configs
#2479 opened Sep 18, 2026 by cjluo-nv Collaborator Loading…
4
Add MLflow tracking flags to megatron_bridge quantize.py
#2477 opened Sep 18, 2026 by kevalmorabia97 Collaborator Loading…
44
Normalize calibrated ONNX request contracts
#2476 opened Sep 18, 2026 by ajrasane Contributor Loading…
3
docs: tolerate limited evaluation response truncation
#2475 opened Sep 18, 2026 by chadvoegele Contributor • Draft
5
docs: verify MLflow delivery and recover existing evaluation exports
#2474 opened Sep 18, 2026 by chadvoegele Contributor • Draft
5
docs: require parent authorization for evaluation resubmissions
#2473 opened Sep 18, 2026 by chadvoegele Contributor • Draft
4
Refactor ONNX Runtime patching into capability modules
#2472 opened Sep 18, 2026 by ajrasane Contributor Loading…
18
[6034518] Fix remote safety benchmark latency
#2467 opened Sep 18, 2026 by ajrasane Contributor • Draft
19
Fix: Release per-layer expert weights in layerwise export under offload
#2466 opened Sep 18, 2026 by Fridah-nv Contributor Loading…
29
feat(quantization): register NVFP4 four-over-six as a real calibration algorithm
#2465 opened Sep 18, 2026 by Fridah-nv Contributor Loading…
40
Fix three windows issues: extension-build timeout, 0xc000001d crash, and config I/O encoding
#2461 opened Sep 17, 2026 by shengliangxu Collaborator Loading…
30
Bring offline KD upgrades such as Ghost Token and Top-P to Megatron K…
#2459 opened Sep 17, 2026 by AAnoosheh Contributor Loading…
20
Gdn qad
#2455 opened Sep 17, 2026 by sychen52 Contributor • Draft
@sychen52
3
Add Llama to Puzzletron v2 puzzletron_v2 Related to feature/puzzletron_v2 branch
#2454 opened Sep 17, 2026 by grzegorz-k-karch Contributor • Draft
@grzegorz-k-karch
4
ProTip! Mix and match filters to narrow down what you’re looking for.