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 supported61 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][Perf] Replace MiniMax-M3 MonoKernel with ATOM full-layer implementation
- [ROCm] Heterogeneous fused shared experts for DeepSeek-V4.1 (native-FP8 shared slot, prefill-shaped batches)
- [Bugfix] Keep valid Hermes tool calls when a later region is malformed
- [Bugfix][Frontend] Honor --response-role and echo in chat derender
- [Tracking] KV event correctness and compatibility
- [Bug][DSv4.1][SM120] enable_adaptive_verification is rejected on SM120 — device-query-lens support is gated to SM90/SM100 only
- [Bugfix][EPLB] Share one NIXL agent per worker across elastic EP reconfigurations, enable MI355 scaling test
- [ROCm] Draft-prepare fastpaths: shared-output dedup + parallel pad-tail + KV-only context insert
- [Frontend] Improve the listen socket and cleanup socket.
- [Fix][MoE] Reuse FlashInfer TRT-LLM MoE workspaces across layers
- Docs
- Python not yet supported