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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Spec Decode] Mask prefix-cache-restored tokens out of the DFlash/DSpark draft context
- [Bugfix][Tool Parser] Stream full single-delta tool calls
- Add KVCrush KV Cache compression for vLLM
- [Attention] Cover missed context segments in the sparse MLA indexer top-k
- [Bug]: Qwen3-Reranker: Process Hang with `/score` Endpoint for Specific Data
- [Rust Frontend][RFC] Anthropic Messages API: /v1/messages and /v1/messages/count_tokens
- [ROCm][MLA][Perf] Fuse decode QK-RoPE + Q-concat + KV-concat + KV-cache write for sparse MLA
- [Performance]: MiniMax-M3 verify-as-decode re-streams the sparse KV from HBM once per draft token
- [Bug]: MXFP4 MoE Marlin fallback crashes with illegal memory access on Hopper (DeepSeek V4, TP+EP) — non-tile-aligned intermediate size
- [Bugfix] Add DSV4-Flash-DSpark gsm8k and pipe kv_quant_mode through SWA MLA unify
- Docs
- Python not yet supported