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
- [vLLM IR] fused_add_rms_norm and maybe_inplace
- [Bugfix] Fix shared expert input for latent MoE in EP+DP (Nemotron-H)
- [Feature]: nightly docker and wheels for ROCm
- [Bug]: #33758 is causing aiohttp/_websocket.c build error
- [Bug]: KV Cache Memory Bottleneck Calculation in Pipeline Parallel (_check_enough_kv_cache_memory in get_kv_cache_configs)
- [Docs] Update docs to include mm processor + encoder benchmarks
- [Observability] Export EPLB balancedness metrics to Prometheus
- Fix realtime transcription never sending transcription.done with slow streaming
- [torch.compile] Remove attention layer name from unified_kv_cache_update
- [BugFix] Fix `fastsafetensors` TP all procs using all GPUs
- Docs
- Python not yet supported