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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix Ray compiled-DAG SHM channel stalls by detaching zero-copy `np.ndarray` logprobs buffers
- [Bugfix]: Fix LoRA loading failure for modules with numeric indices (e.g., to_out.0 in Diffusion Transformers)
- [NVFP4] Support NVFP4 dense models from `modelopt` and `compressed-tensors` on AMD Instinct GPUs, on Hopper, Ampere, etc. through emulation
- [Performance] Add is_reasoning_end_streaming() override to GptOssReasoningParser
- [Bugfix] Fix tool call ID collision in Anthropic endpoint
- [NVFP4] Support NVFP4 MOE models on AMD Instinct, Nvidia Ampere, Hopper through NVFP4 MOE emulation
- [Bugfix] VllmRunner should clear memory on exit in single process mode
- [Bug] Fix HIP build in Docker: filter offload-arch stderr from compiler flags
- Fix: Suppress spurious cuDeviceGetAttribute errors in cumem_allocator
- [XPU]Enhance environment collection for Intel XPU and optimize layout
- Docs
- Python not yet supported