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
- [Benchmark] Add standalone rust vllm-bench image
- [Bugfix][Spec Decode] Restore DeepSeek-V4 DSpark draft quantization
- [qwen3] correct linear_attn norm and a_log parameter dtype to F32 for qwen 3.5 series
- [Bug]:Anthropic Messages API: x-api-key authentication header not supported — only Authorization: Bearer works
- [V1 Scheduler] Fix Priority Queue Preemption Re-admission (#41951)
- [XPU] Enable MiniMax-M3 on non-CUDA backends: portable fallbacks for CUDA-only paths
- [Bug]: OffloadingConnector CPU tier leaks its /dev/shm mmap file on any unclean exit (including SIGKILL)
- [Bug]: [ROCm] v0.26.0 release image: NaN logits from AITER fused-MoE path on gfx942 (Qwen3.5-397B-A17B-FP8) — fixed on main, requesting 0.26.x backport
- [Bug][Spec Decode]: DFlash fused-KV projection calls F.linear on a sliced qkv_proj weight — breaks (and can silently corrupt) any weight-quantized drafter
- Accept x-api-key header in AuthenticationMiddleware
- Docs
- Python not yet supported