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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: vLLM + FlexAttention crashes with torch._dynamo.exc.InternalTorchDynamoError: AcceleratorError: CUDA error: misaligned address
- [Attention] Remove unused slot mapping from standard metadata
- [Attention] Remove unused slot mapping from FlashAttention metadata
- [Bugfix] Prevent stale multiproc RPC deadlines from becoming unbounded waits
- [Bugfix] Fix double reduce in flashinfer_nvlink_two_sided and flashinfer_nvlink_one_sided backends
- docs: clarify NIXL KV transfer metrics aggregation
- [Compile] Fix compile warning with topk softplus sqrt
- [Refactor] Merge `select_gpt_oss_mxfp4_moe_backend` and `select_mxfp4_moe_backend`
- [RFC]: Custom graph dumping for vLLM-compile and depyf deprecation
- [CI Failure]: mi355_2: NixlConnector PD + Spec Decode acceptance (2 GPUs)
- Docs
- Python not yet supported