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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Metrics] Count client-aborted requests in vllm:request_success
- [Bug]: Sparse weight patches fail on tied embeddings when lm_head and embed_tokens land in different chunks
- [ROCm][DSv4.1][Perf] Route gfx942 mHC seams through aiter mhc_fused_post_pre_delayed
- [Attention] FA4 hd512 GQA on Blackwell for DiffusionGemma
- [ROCm][DSv4.1][Perf] Use AITER FlyDSL GEMM for DeepSeek V4.1's 32x32 MXFP8 linears on gfx950
- [Bug]: TRITON_MLA decode exceeds shared memory on sm_120 (RTX PRO 6000 / RTX 5090): "Required: 102400, Hardware limit: 101376"
- [Docs][Metrics] Document prefix cache hit rate monitoring and add a Gā¦
- [BugFix] Keep tied embedding patches valid across weight-patch chunks (#60151)
- [Bugfix] Make collect_env list the running interpreter's packages under uv
- [Security] Bound HF tojson indent allocation in Rust chat templates
- Docs
- Python not yet supported