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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: MooncakeStoreConnector produces N× write amplification under DCP for MLA models
- [Bugfix][SM120][MLA] Disable dense prefill for FlashInfer sparse MLA
- [Bug]: cpu_offload_gb silently no-ops on Model Runner V2 — offloader never installed, model loads fully on-GPU with no warning
- [Bug]: Kimi K3 tool parser streams the raw <|close|>message<|sep|> marker into content
- [BugFix] Bind fault-tolerance DP ports before publishing them
- [Bug]: Inkling (InklingForConditionalGeneration) fails on SM120 — tml_fa4 attention lacks paged-KV support
- [ROCm] Enable fused QK-norm+RoPE+gate Triton kernel for Qwen3-Next/Qwen3.5
- [Core][KVConnector] Connector "ready" state for asynchronous connector startup
- [Bug]: System crash: Rust frontend aborts the process on prompt logprobs for a zero-token prompt
- [Bugfix] Pad assertion error in truncate_computed_blocks due to lagging mamba lookup
- Docs
- Python not yet supported