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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [CI][RL] Add E2E test suite for sleep/wake/pause/weight-update lifecycle
- [Bugfix] Reject sampling params unsupported by diffusion models
- [Kernel] Single-read fast path for fused RMSNorm + dynamic per-token FP8 quant
- [Bug]: RuntimeError: Already borrowed still occurs with bad_words despite thread-safe tokenizer wrapper
- [Draft][Rust Frontend] Use Dynamo parser for DeepSeek V4
- [Perf] Reuse topk SparseMatrix routing metadata in GPT-OSS MoE forward
- [Bug]: Integer overflow in permute_cols
- [Frontend] Add completion_token_details to usage object in Chat Completions response body
- [Bug]: Engine core dies on KV-connector load failure for hybrid-KV models — `_update_requests_with_invalid_blocks` assumes a single KV cache group
- [Bugfix] Keep intermediate prefill chunks mamba-block-aligned with spec decode
- Docs
- Python not yet supported