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 supported44 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][ROCm] Fix OOB query read in paged_attention_rocm for head_size < 128
- [Bug]: MTP speculative decoding crash with illegal memory access on long sequences (Qwen3.6-27B-FP8, v0.19.1)
- [Core] Prevent zero-collapse deadlock in _mamba_block_aligned_split
- [Core] Fix Run:ai streamer loading for Mistral-format safetensors
- [Tracing] Add cache read tokens, finish reasons, and new standard OTel attributes
- [Feature]: Deepseek V4 cannot run ,Please support SM120 GPU,example rtx5090 rtxpro6000
- [Bug]: TurboQuant KV + spec-decode + chunked-prefill crashes CUDA graph capture at query_start_loc.tolist() in continuation-prefill path (Qwen3-Next hybrid dense)
- init
- [fix] mismatch dim during capture graph if with --gpu-memory-utilization
- [Core] Token-level DP load balancing for prefill-heavy workloads
- Docs
- Python not yet supported