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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Extract guidellm results
- [Bug]: No available shared memory broadcast block found in 60 seconds. This typically happens when some processes are hanging or doing some time-consuming work (e.g. compilation, weight/kv cache quantization)
- [Perf][DeepSeek-V3] Dynamic MLA/MHA Routing for Sub-1024 Token Prefill (~3x TTFT Speedup)
- Make DeepSeek V2/V3/R1 RMSNorm consistent with DeepSeek impl
- [Bug]: Qwen3-Omni Model Fails when try to l
- feat(responses): add WebSocket mode for Responses API
- Grpc renderer
- [Bug] CompressedTensorsWNA16MarlinMoEMethod registers g_idx params unconditionally, crashes with actorder=null AWQ MoE models
- [Feature]: Profiler num_steps
- [Feature]: Performance Optimization for Model Runner V2
- Docs
- Python not yet supported