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
- Add unit tests for fp8 output fusion of triton_attn
- [CI Failure]: mi325_1: Language Models Test (MTEB)
- [KVConnector] Clean up redundant code in KV connectors
- [ROCm][Kernel] Add GFX11 (RDNA3) support for wvSplitK skinny GEMM kernels
- [Bugfix] Fix step3p5 reasoning with interleaved thinking
- [vLLM/v1][sample] Refactor the exponential_ method calling to improve performance of TopKTopPSampler
- Revert "[MISC] Fix Tensor Parallelism for Quantized Mamba Models with n_groups=1 (#33257)"
- add extras dict to FinishedRequestStats to enable stat logger plugins…
- [Bug] Fix MLPSpeculatorConfig missing num_attention_heads attribute
- [Frontend] Add per-request stream interval control with time-based throttling
- Docs
- Python not yet supported