vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- fix(kv-cache): allow TurboQuant on hybrid models
- [WIP]Support DeepSeek V4 flash on SM120 with Triton fallback
- [Bugfix] Fix `RuntimeError: Already borrowed` by enforcing one tokenizer per thread and one thread in threadpool
- [NIXL][Bugfix] Fix block indexing in KV cache transfer for blocks-first layouts
- [Feat][RL] FusedMoE EP-sharded routed-expert weight load
- [KVConnector] Introduce `bind_scheduler_state` API
- [Bugfix] Fix partial tool-call marker leaking as content during reasoning-to-tool transition
- [Frontend] support extra_body params for /v1/messages (Anthropic)
- [Model] Add RWKV-7 (Goose) inference support
- [Feat][CPU] Enable Gated DeltaNet Attention (Qwen 3.5 / 3.6)
- Docs
- Python not yet supported