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
- [Quantization] Use torch.from_numpy to avoid deep copy when iterate GGUF weights
- [Feature]: GGUF model with architecture qwen3vlmoe is not supported yet.
- [Bug]: `--pipeline-parallelism>2` results in `RayChannelTimeoutError`
- [Bug]: LongCat-Flash fails to start with TorchDynamo due to “Data-dependent assertion failed” in FusedMoE
- [Performance]: Prefill TTFT and latency both increased
- [Bug]: Build vllm on Apple silicon: libc++abi error
- Using os.sched_yield() releases the CPU so quickly that it causes 100% CPU utilization.
- [Bug]: engine monitor outputs unexpected error though the engine works well
- [Bug]: [H200] DeepSeek-R1 EP 1.5x TTFT due to MoE backend behavior changes
- [Feature]: More control over expert parallelism (--moe_ep_size, --moe_tp_size)
- Docs
- Python not yet supported