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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Zero-fill rematerialized weights so reload preserves padding
- [XPU] Alias is_current_stream_capturing to XPU in cuda wrapper
- [Bugfix][Gemma4] Keep image bidirectional attention within the sliding window on the V2 model runner
- [CPU] check some more implementation assumptions on kv layout
- [Bug]: [XPU] Multi-GPU TP serving hangs on Intel Arc Pro B60 with torch 2.13 wheels (oneCCL 2022.x): warmup allreduce never returns, GuC timeouts, DEVICE_LOST`
- [Bugfix][Core] Don't cache the reader's ring slot across acquire_read retries
- [Regression]: MiniMax-M3 leading `</mm:think>` bypasses the reasoning parser on v0.26.0 and current main
- [Bugfix][NIXL] Handle decode allocating more blocks than prefiller in prefix caching
- [Bugfix] Validate tensor dtypes in the moe_wna16 GEMM op wrappers
- [ROCm][Bugfix] Keep the MLA query in bf16 for AITER Gluon fp8 KV decode
- Docs
- Python not yet supported