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 supported18 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Remove pooling multi task support. (Hold off until v0.20.0)
- Fix cudagraph max capture size upper bound
- fix: add qk_layernorm support for Phi models
- [ROCm][perf] fix Aiter sparse MLA with MTP>1
- [Bugfix] Fix concat_mla_q kernel for float32 dtype
- [LMCache CI]: add HND interface protection
- [ROCm] Add UE8M0 scale packing for Triton silu_mul_quant
- replace cuda_device_count_stateless() to current_platform.device_count()
- [RFC]: Unify the function of getting device count
- fix: handle FakeTensorMode patching for PyTorch compatibility
- Docs
- Python not yet supported