Skip to content

Pull requests: NVIDIA/Model-Optimizer

New pull request New
252 Open 1,440 Closed
252 Open 1,440 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 model-aware guided Puzzletron setup puzzletron_v2
#2117 opened Aug 8, 2026 by j-rausch Contributor • Draft
3
Add Qwen 3.5 0.8B Puzzletron configs puzzletron_v2
#2116 opened Aug 8, 2026 by j-rausch Contributor • Draft
16
[NVBug: 6563509] Harden meta-device skeleton build; drop Phi-3-vision / Phi-4-multimodal PTQ support cherry-pick-0.46.0
#2115 opened Aug 7, 2026 by cjluo-nv Collaborator Loading…
20
Fail closed on Puzzletron correctness failures puzzletron_v2
#2114 opened Aug 7, 2026 by j-rausch Contributor Loading…
10
feat(megatron-bridge): SFT-masked data support in distillation
#2113 opened Aug 7, 2026 by yueshen2016 Contributor Loading…
26
fix(megatron): restore untied output_layer quantization under Megatron-Bridge
#2112 opened Aug 7, 2026 by yueshen2016 Contributor Loading…
27
Add downstream eval to puzzletron v2 puzzletron_v2
#2104 opened Aug 7, 2026 by grzegorz-k-karch Contributor Loading…
@grzegorz-k-karch
22
Fix AA-next OpenHands timeout guidance
#2094 opened Aug 6, 2026 by Edwardf0t1 Contributor Loading…
8
Resolve tied weights by declared name in HF export (FSDP/offload-correct)
#2092 opened Aug 6, 2026 by juhi10071998 Contributor • Draft
3
Fix clip backward with broadcasted constant bounds
#2089 opened Aug 6, 2026 by Robertboy18 Loading…
3
refactor(export): split unified_export_hf into layered modules
#2088 opened Aug 6, 2026 by Fridah-nv Contributor Loading…
22
docs: rebuild the unified HF deployment support matrix from the deploy test suite (NVBug 6550792) cherry-pick-0.46.0
#2087 opened Aug 5, 2026 by Edwardf0t1 Contributor Loading…
11
Add FastGen quantization-aware distillation
#2085 opened Aug 5, 2026 by jingyu-ml Contributor • Draft
2
[NVBUG: 6562021] Fix vLLM FlashAttention KV cache layout handling
#2084 opened Aug 5, 2026 by sychen52 Contributor Loading…
@sychen52
18
Add FP8 Vision Encoder quantization for Qwen3-VL and Qwen3.5
#2083 opened Aug 5, 2026 by mpariente-nvda Loading…
7
Fix/tied weight export identity
#2081 opened Aug 5, 2026 by chadvoegele Contributor Loading…
13
fix(specdec): correct resume and bound staging in the vLLM hidden-state dump
#2080 opened Aug 5, 2026 by yeyu-nvidia Contributor Loading…
14
fix(autotune): pre-check remote board connectivity before benchmark
#2078 opened Aug 5, 2026 by willg-nv Contributor Loading…
19
Puzletron v2 dockerfile puzzletron_v2
#2077 opened Aug 5, 2026 by chochowski Contributor Loading…
6
feat(megatron-bridge): adopt TEGroupedMLP per-expert quantizers (#1550) for W4A16 NVFP4 four_over_six
#2072 opened Aug 5, 2026 by yueshen2016 Contributor Loading…
20
Add Qwen-Image DMD2 QAT and PEFT-backed SVDQuant
#2069 opened Aug 5, 2026 by jingyu-ml Contributor • Draft
4
Bug fix: 6542481 cherry-pick-0.46.0
#2064 opened Aug 4, 2026 by sugunav14 Contributor Loading…
39
[skill] evaluation: align nel-next TB2.1/SWE-bench with golden toolchain
#2063 opened Aug 4, 2026 by cjluo-nv Collaborator Loading…
14
Preserve HF PTQ checkpoint sidecar files [NV BUG 6491822] cherry-pick-0.46.0
#2060 opened Aug 4, 2026 by jenchen13 Contributor Loading…
54
Fix FSDP2 handling for tied embeddings
#2059 opened Aug 3, 2026 by realAsma Contributor • Draft
8
ProTip! Filter pull requests by the default branch with base:main.