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
- [Kernel] Skip out-of-window KV blocks in paged decode sliding-window path
- [Bug]: if passed temperature=0.0 there is no output of its value in telemetry span
- [Bugfix][ROCm][CI] Fix qk_norm_rope_kvcache fusion test for packed KV cache layout
- [XPU] Enable XPU blockfp8 for DSv3
- [CI][torch nightly] mamba-ssm build fails under torch 2.14 nightly - forces -std=c++17 but ATen now requires C++20
- [XPU] Add Kimi Delta Attn(KDA) Support
- [Do Not Merge!] Update vllm to point to flash-attention commit that builds FA3 with torch stable API. (Retry)
- [CI] Build mamba-ssm with C++20 for torch 2.14 nightly compatibility
- [Weight processing] Copy over `new_data` attributes in `replace_parameter`
- Fix GLM-4.1V vision TP fallback for non-divisible attention heads
- Docs
- Python not yet supported