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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: `previous_response_id` drops function_call/function_call_output from stored context in Responses API
- [Bug]: AttributeError in mla_attention.py L2094 (_compute_prefill_context) on long prefill with AWQ model — regression after PR #34695
- [Bug]: Qwen3-VL-MoE crashes at init with pipeline parallelism ("No model architectures are specified")
- [Bugfix] Qwen3-VL(-MoE): pass architectures to with_hf_config for pipeline parallelism
- [Bug]: EagleMistralLarge3Model crashes with AttributeError: 'use_mha' on vLLM 0.21.0
- [Bug]: b12x NSA+MTP speculative decoding hangs on PCIe TP=8 — NCCL topology-aware scheduling fix
- [Bug]: Gemma4 26B-A4B fails because GELU_TANH is unsupported in CPU fused MoE path
- CUDA illegal memory access in FP8 MoE moe_permute with cutlass backend at batch size 8192
- [Kernel] Support UE8M0 scales in fused SiLU block quant
- [Bug]: OpenAIServingChat silently requires new openai_serving_render kwarg since v0.18
- Docs
- Python not yet supported