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
- [Feature]: Central fusion work tracker
- [ROCm] Fix AITER ops fake impl and minor bugs
- [ROCm][v0.16.0] Qwen3-VL-30B-A3B-Instruct-FP8 fails to start with NotImplementedError: No FP8 MoE backend supports the deployment configuration
- [Bugfix] Guard fabric handle APIs for CUDA < 12.4 compatibility
- Perf: Optimize CPU detokinzation for long decodes
- set VLLM_USE_BYTECODE_HOOK to 0 by default
- [WIP][Proof of concept] Overlap model loading and torch.compile
- [Docs] Add doc note about building for free-threaded Python.
- [RFC]: Add InstantTensor Support in vLLM
- Set default value for --ready-check-timeout-sec flag in benchmarking script
- Docs
- Python not yet supported