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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: 投机推理时,异步调度场景,将 -1 作为spec token 赋值给了 input_ids
- benchmark_serving: throughput collapses at 50K+ context due to aiohttp read buffer and shared session
- [Fix] Resolve docker build-time LegacyKeyValueFormat warnings
- [Bug]: Mismatch between batch queue size and max-num-seqs
- [Bug]: Qwen3.5-122B-A10B Engine hangs at Prefill phase under high concurrency (40 reqs) with multi-node PP=2 on dual 4090D nodes
- [Bug]: Turboquant attention crashes on A100 when serving BF16 models with FP8 KV cache
- [Usage]: does vllm support Qwen3_5ForCausalLM architecture inference? not just Qwen3_5ForConditionalGeneration?
- [Bug]: Index out of bounds in TurboQuant KV Cache kernel with Qwen3 during high-concurrency 32k context benchmark
- [Performance]: vllm 19.0 online server测试波动偏大
- [Bug]: Inconsistent KV Cache reporting and system hang on long context requests (Gemma-4 26B AWQ Int4)
- Docs
- Python not yet supported