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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Kernel] Make Marlin MoE route alignment deterministic
- [Rust Frontend] Extend the existing gRPC service protocol
- [Performance]: Official FP8 checkpoint ~40% slower at bs=1 than runtime fp8 quant of same model (Qwen3-4B, RTX 4090, v0.24.0)
- [Bugfix][Scheduler] Let pooling chunked prefill use full context
- [Bug][ROCm] Triton kernel_paged_attention_2d illegal memory access (hipErrorLaunchFailure) on gfx950 (MI350X) under long-context decode
- feat(frontend): session id plumbing into requests
- [RFC][Feature]: First-class session id for conversation aware routing
- [ROCm] Don't re-quantize bf16 MLA kv_b_proj to fp4/fp8 for GLM MoE DSA
- [Bugfix][Hardware] DeepSeek-V4 o_proj fp8 einsum NaNs on SM12x: use SM90-style raw f32 block scales
- [Core] Use capture_error_mode="thread_local" on all CUDA-graph capture paths
- Docs
- Python not yet supported