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 supported23 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Usage]: How to enable the grpc api with vllm serve?
- [BugFix] Handle dict values in YAML config by converting to JSON in config file
- replace `with torch.cuda.stream()`
- [RFC]: Support FP8 LoRA inference
- [Frontend] Add tool_choice=required support for GPT-OSS Harmony models
- [Feat][SM90] Add cutlass int4 x bf16 MoE
- [Bugfix] Fix inconsistent embeddings between AsyncLLM and LLM
- Isolate VLLM_CACHE_ROOT per test to fix torch.compile cache reuse
- [Bug]: LoRA MoE Not Matching HF Output
- [Benchmark] Add vllm bench iterations for prefill/decode measurement
- Docs
- Python not yet supported