rvLLM: High-performance LLM inference in Rust. Drop-in vLLM replacement.
active 2026-03-28 → 2026-07-07 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 102 days from 2026-03-28 to 2026-07-07. Pushes: 273 total, peak 36 in a day. Pull requests: 5 total, peak 1 in a day. Issues: 4 total, peak 2 in a day. Comments: 16 total, peak 6 in a day. Stars: 165 total, peak 32 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 |
|---|---|---|---|---|
| m0at | 284 | 273 | 1 | 8 |
| gracee3 | 9 | 0 | 3 | 5 |
| hersche | 2 | 0 | 0 | 2 |
| SarahLacard | 1 | 0 | 0 | 1 |
| sentivfan | 1 | 0 | 0 | 0 |
| adybag14-cyber | 1 | 0 | 1 | 0 |
| chatgpt-codex-connector[bot] | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Pull request#62m0at2026-06-12 18:41
- Issue comment#46m0at2026-05-18 02:32Mistral 3.5 w working vision-support (+ Vision + Qwen 3.6 (+ inference-server + NVFP4-kv)
- Issue comment#42hersche2026-04-23 22:45sm121/GB10-integration
- Issue comment#42hersche2026-04-21 06:59sm121/GB10-integration
- Issue comment#41m0at2026-04-14 18:02Does rvllm support MiniMax2.7?
- Issue comment#33m0at2026-04-14 17:56Implement full end-to-end Qwen3.5 support
- Issue comment#20m0at2026-04-14 17:55Add native multimodal Responses runtime support
- Pull request#31adybag14-cyber2026-04-03 23:10
- Issue#21m0at2026-04-02 17:45Populate Responses include payloads instead of only accepting include values
- Issue comment#28m0at2026-04-02 17:15Add Blackwell GB10 (sm_121) support: FP8 + INT4 GPTQ inference
- Issue comment#23gracee32026-03-30 01:39Support conversation state objects on /v1/responses
- Issue comment#19gracee32026-03-30 01:39Expand Responses API compatibility support
- Issue#20gracee32026-03-30 01:36Add native multimodal Responses runtime support
- Issue comment#18gracee32026-03-30 01:31Support multimodal input parts on /v1/responses
- Issue comment#6gracee32026-03-30 00:46Add GPT-OSS 20B CUDA support
- Issue comment#6gracee32026-03-30 00:41Add GPT-OSS 20B CUDA support
- Pull request#13gracee32026-03-30 00:41
- Issue comment#7m0at2026-03-30 00:01Add end-to-end beam search support
- Issue comment#10m0at2026-03-29 21:04Add experimental Qwen3.5 inference compatibility
- Issue comment#5m0at2026-03-29 21:03Fix all clippy warnings/errors, add AGENTS.md and contributor templates
- Issue#9m0at2026-03-29 20:29Considering add vllm-omni
- Issue#12sentivfan2026-03-29 19:27Needs Support for SM121
- Pull request#8gracee32026-03-29 00:57
- Pull request#6gracee32026-03-28 23:45
- Issue comment#3SarahLacard2026-03-28 12:18fix(engine): make Hugging Face snapshot resolution index-aware
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 165 stars here means stars gained during the window, not the repo's star count.