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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Aiter][ROCm] QKV-split + QK-RMSNorm + RoPE + KV-cache-write fusion
- [Bug]: vllm serve hangs permanently with data_parallel_size > 1 on multi-node Ray cluster (MoE model, --enable-expert-parallel)
- [Bug]: compressed-tensors kv_cache_scheme overrides kv_cache_dtype to fp8 during MTP speculative decoding, causing CUDA crash on SM89 (L4/RTX4090)
- [Performance]: Cold start takes ~5 min for nvidia/Qwen3.6-35B-A3B-NVFP4 on RTX 5090 (sm_120) with vLLM
- [Feature]: Avoid duplicate KV block allocation for shared external-prefix hits
- Add release_kv_cache() API
- [Core] FlowPrefill: adaptive sub-chunk preemption for v1 Scheduler
- fix: replace assert with proper exceptions in SamplingParams validation
- [Bug]: Qwen3.5 397B NVFP4 DEP8 mixed prefill-decode step 6x times longer than decode-only step
- [Model] TEMP Fix for DFlash SWA PR (#40898)
- Docs
- Python not yet supported