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 supported46 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- vLLM 0.19 may lose tool calls for Qwen/Qwen3.5-35B-A3B-FP8 when XML tool_call is emitted inside <think>
- [Transformers/Bugfix] Fix Gemma4 MoE top_k lookup + duplicate kv_seqlens in op schema
- [Bugfix][MoE] Fix hardcoded SharedExperts output buffer size for DBO ubatches
- [Bug]: runai_safetensors_weights_iterator yields tensors in nondeterministic order, breaking FP8 inference on some platforms
- [Bug]: Gemma 4 MoE (26B-A4B) — runtime MXFP4 quantization crashes during weight loading in fused MoE layer
- [Bug]: torch.distributed.DistNetworkError: The server socket has failed to listen on any local network address. port: 29500, useIpv6: false, code: -98, name: EADDRINUSE, message: address already in use
- [Perf] Remove per-step KV offload touch, touch once at request_finished
- Qwen-3.5 9B often producing repetitive/garbled output with Intel Backend
- [Bug]: Gemma 4 MoE (26B-A4B) crashes with `--data-parallel-size > 1` — AssertionError in cuda_communicator all_gather
- [Performance]: Qwen 3.5 27B Prefix Caching
- Docs
- Python not yet supported