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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Misc] Add token breakdown to throughput benchmark JSON output
- Remove duplicate fake registration implementations for gptq_marlin_repack and awq_marlin_repack operations.
- [Feature]: [CPU Backend] Grouped GEMM kernel for CPU backend
- [RFC]: Force EOS generation when Structured Output Grammar is terminated
- [Feature]: Allow v2 weight loader to accept pre-sharded TP tensors
- [Bug]: Ministral 3 - streaming tool call not working
- [draft] OptionalCUDAGuard --> DeviceGuard
- [Bug]: `pplx-kernels` fails to load in vLLM container
- TP > 1 with Ray Serve: Use Multiprocessing Executor (Not Ray Executor)
- [Bug]: vLLM v0.12.0: CUDA Illegal Memory Access During CUDA Graph Capture on Multi-Node GH200 (TP=4, PP=2)
- Docs
- Python not yet supported