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
- Replace VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE env var with max_num_batched_tokens
- [Bugfix] Handle None compilation times in v1 Executor initialize_from_config
- [Bugfix] Fix EAGLE3+async crash: clear stale spec_token_ids for unscheduled requests
- [Tracking Issue]: Mamba Heterogeneous TP for NIXL P/D Disaggregation
- [Usage]: Improve error handling when task='classify' is used with decoder-only models (e.g., Qwen, Llama, Mistral)
- [Bug]: RuntimeError: 基于megatron grpo Qwen3-Omni模型时,出现RuntimeError: Event device index does not match recording stream's device index
- Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
- [Spec Decode][Quantization] fallback quant_config to None for unquantized MTP draft model
- Early Stopping for Ouro models
- [Bug]: Prefetch CPU offload OOMs; `VLLM_WEIGHT_OFFLOADING_DISABLE_PIN_MEMORY` must be implemented
- Docs
- Python not yet supported