A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
active 2025-12-07 → 2026-08-11 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 248 days from 2025-12-07 to 2026-08-11. Pushes: 5,574 total, peak 123 in a day. Pull requests: 358 total, peak 12 in a day. Issues: 140 total, peak 10 in a day. Comments: 2,104 total, peak 43 in a day. Stars: 276 total, peak 8 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| copy-pr-bot[bot] | 1.7K | 1.6K | 0 | 100 |
| github-actions[bot] | 1.4K | 1.3K | 8 | 84 |
| coderabbitai[bot] | 960 | 4 | 1 | 564 |
| kevalmorabia97 | 627 | 381 | 30 | 110 |
| realAsma | 366 | 102 | 7 | 121 |
| cjluo-nv | 342 | 104 | 17 | 121 |
| h-guo18 | 318 | 187 | 27 | 45 |
| ChenhanYu | 309 | 196 | 23 | 47 |
| jingyu-ml | 232 | 149 | 22 | 29 |
| shengliangxu | 227 | 135 | 10 | 43 |
| ajrasane | 213 | 86 | 7 | 85 |
| danielkorzekwa | 211 | 161 | 8 | 29 |
| meenchen | 189 | 98 | 14 | 40 |
| Edwardf0t1 | 189 | 86 | 10 | 49 |
| yeyu-nvidia | 189 | 139 | 10 | 21 |
| kaix-nv | 175 | 110 | 8 | 30 |
| willg-nv | 151 | 0 | 10 | 72 |
| gcunhase | 145 | 14 | 8 | 71 |
| kinjalpatel27 | 143 | 82 | 7 | 26 |
| jenchen13 | 130 | 86 | 6 | 18 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#2115codecov[bot]2026-08-07 20:49[NVBug: 6563509] Harden meta-device skeleton build; drop Phi-3-vision / Phi-4-multimodal PTQ support
- Issue comment#2115github-actions[bot]2026-08-07 20:44[NVBug: 6563509] Harden meta-device skeleton build; drop Phi-3-vision / Phi-4-multimodal PTQ support
- Issue comment#2024gcunhase2026-08-07 20:41[OMNIML-5613] Quantize ResNet residual adds in torch ONNX example
- Issue comment#2024gcunhase2026-08-07 17:54[OMNIML-5613] Quantize ResNet residual adds in torch ONNX example
- Issue comment#2092codecov[bot]2026-08-07 16:47Resolve tied weights by declared name in HF export (FSDP/offload-correct)
- Pull request#2051j-rausch2026-08-04 07:42
- Issue comment#1971ChenhanYu2026-07-28 03:43docs: add announcements landing page
- Issue comment#2014github-actions[bot]2026-07-24 12:42Reorganize 0.46 Changelog
- Issue comment#1963github-actions[bot]2026-07-11 00:37feat(quant): skip max-calib forward when no activation needs data
- Issue comment#1928coderabbitai[bot]2026-07-07 11:34[6403893][ONNX][AutoCast] Fix false-success TRT parse for large ModelProto
- Issue#1895h-guo182026-07-05 02:17warnings.warn(f"RealQuantLinear: No real-quant GEMM found: {self}.")
- Issue comment#1872github-actions[bot]2026-07-03 18:08Create a user guide: ModelOpt for Researchers: Fast Experimentation Workflows
- Issue#1895zewenli982026-07-02 22:19warnings.warn(f"RealQuantLinear: No real-quant GEMM found: {self}.")
- Pull request#1892arham7662026-07-02 21:27
- Issue comment#1884copy-pr-bot[bot]2026-07-02 00:57Add LAQ QAD recipes
- Issue comment#1878copy-pr-bot[bot]2026-07-01 19:58Add normalized and group-boundary AutoQuant scoring
- Pull request#1874kevalmorabia972026-07-01 16:23
- Issue comment#1869realAsma2026-07-01 02:27Refine DeciLM dtype handling in HF PTQ
- Pull request#1868sugunav142026-06-30 17:24
- Pull request#1863Edwardf0t12026-06-30 08:01
- Issue comment#1858codecov[bot]2026-06-30 00:28fix(export): list unquantized MoE routers in exclude_modules (NVBug 5718750)
- Issue comment#1857realAsma2026-06-29 23:41Fix HF PTQ empty-init dtype kwargs
- Issue comment#1845hychiang-git2026-06-28 05:44docs(eval): add NEL v0.3.0 migration guide + example configs
- Issue comment#1845coderabbitai[bot]2026-06-28 03:32docs(eval): add NEL v0.3.0 migration guide + example configs
- Issue comment#1846github-actions[bot]2026-06-28 03:21final norm
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 276 stars here means stars gained during the window, not the repo's star count.