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
- [Rust Frontend] Tool-call argument parsing diverges from the Python parsers (coercion, whitespace, unions)
- [Frontend] Cohere chat v2 api support
- [Rust Frontend] Match Python union-type coercion precedence
- [Bug]: GPT-OSS models silently ignore unsupported content types (input_file, etc.)
- [Bug]: Concurrent temperature=0 non-determinism in vLLM, FLASH_ATTN batch-invariant path on Hopper
- [Kernel] Add Triton warmup compile-key tracing
- [Bug] Avoid Triton 3.8 nvidia cuInit poisoning forked CUDA init
- [Bug]: Native MTP speculative decoding degenerates into garbage token loops on deep agentic conversations (Qwen3-MoE)
- [RFC]: Extension points for backends whose physical layout isn't a permutation of the logical layout (weights, quant scales, KV-cache, MLA, EP)
- Revert "[MoE Refactor] Standardize Humming MoE experts + utilities" (#43373)
- Docs
- Python not yet supported