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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Mistral's "always adjust_request" grammar path rebuilds the tool parser and compiles regex over the full vocab on the main event loop, on every request — even tool_choice="none"
- [Bug]: Qwen3 parser turns tool-call markup the model quotes into real tool calls (names outside request.tools, and duplicates of offered ones)
- [Rocm][Bugfix][Quantization] Auto-enable EP for Qwen3.8-Flash-Next-FP8 when FP8 MoE TP would fail block_n alignment
- [Bugfix][Distributed] Preserve symmetric collective outputs
- [Kernel][ROCm] kv split decoding kernel for RDNA3/4
- [Perf][DSv4.1] Keep activations MXFP8 between DeepGEMM kernels
- [ROCm][Perf] Parallelise AITER MLA page-index expansion over token chunks
- [Bug]: `/v1/messages` returns two different error envelopes. Request-validation errors come back in the OpenAI shape, with a Python repr inside the message
- [BugFix] Keep echo prompt text when return_token_ids is set
- [Bugfix][ROCm] Preserve config during GPU memory profiling
- Docs
- Python not yet supported