A high-throughput and memory-efficient inference and serving engine for LLMs
active 2025-02-07 → 2026-08-23 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 563 days from 2025-02-07 to 2026-08-23. Pushes: 704 total, peak 16 in a day. Pull requests: 48 total, peak 4 in a day. Issues: 0 total, peak 0 in a day. Comments: 29 total, peak 7 in a day. Stars: 0 total, peak 0 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 |
|---|---|---|---|---|
| benchislett | 292 | 289 | 2 | 1 |
| vadiklyutiy | 147 | 147 | 0 | 0 |
| hjjq | 60 | 60 | 0 | 0 |
| wangshangsam | 56 | 44 | 4 | 5 |
| dependabot[bot] | 52 | 7 | 34 | 11 |
| maxyanghu | 43 | 35 | 1 | 4 |
| b-mu | 30 | 25 | 1 | 1 |
| zhandaz | 29 | 25 | 3 | 0 |
| leo-cf-tian | 21 | 20 | 1 | 0 |
| johncalesp | 18 | 18 | 0 | 0 |
| wzhao18 | 10 | 10 | 0 | 0 |
| github-actions[bot] | 6 | 0 | 1 | 5 |
| Victor49152 | 6 | 6 | 0 | 0 |
| ybgao-nvidia | 6 | 6 | 0 | 0 |
| shaharmor98 | 4 | 4 | 0 | 0 |
| soodoshll | 3 | 0 | 1 | 1 |
| arpera | 3 | 3 | 0 | 0 |
| aaron-tang-centml | 2 | 2 | 0 | 0 |
| Anerudhan | 2 | 0 | 0 | 0 |
| nimapourjafar | 2 | 2 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#47soodoshll2026-03-15 23:28
- Issue comment#45github-actions[bot]2026-02-10 23:04Add TransformerEngine FP8 for image encoder
- Pull request#43wangshangsam2026-02-10 04:42
- Pull request#40zhandaz2026-02-08 06:08
- Pull request#41zhandaz2026-02-08 04:40
- Pull request#33b-mu2026-02-08 04:10
- Issue comment#38soodoshll2026-02-05 22:00Nvimgcodec + tensor ipc
- Pull request#36dependabot[bot]2026-01-31 23:02
- Pull request#36dependabot[bot]2026-01-31 23:02
- Pull request#34wangshangsam2026-01-30 07:45
- Pull request#32wangshangsam2026-01-30 07:24
- Issue comment#30b-mu2026-01-26 02:27Add Flashinfer cudnn Backend for ViT
- Pull request#30wangshangsam2026-01-26 00:45
- Pull request#29zhandaz2026-01-25 02:49
- Pull request#30maxyanghu2026-01-23 21:54
- Pull request#27dependabot[bot]2026-01-16 19:32
- Issue comment#26wangshangsam2026-01-15 03:53[Docker] Remove CUDA compatibility library loading; fixes #32373
- Issue comment#26wangshangsam2026-01-15 03:52[Docker] Remove CUDA compatibility library loading; fixes #32373
- Issue comment#26huydhn2026-01-15 03:51[Docker] Remove CUDA compatibility library loading; fixes #32373
- Issue comment#26github-actions[bot]2026-01-15 03:50[Docker] Remove CUDA compatibility library loading; fixes #32373
- Issue comment#14dependabot[bot]2026-01-13 20:56Bump mlflow from 2.22.0 to 3.5.0rc0 in /requirements
- Pull request#25dependabot[bot]2026-01-13 20:56
- Pull request#24dependabot[bot]2026-01-13 20:24
- Pull request#24dependabot[bot]2026-01-13 20:24
- Issue comment#17dependabot[bot]2026-01-09 00:33Bump werkzeug from 3.1.3 to 3.1.4 in /requirements
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.