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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Reasoning] muse_glimmer: enable thinking_token_budget
- [Bugfix][Model] Cap Voxtral Realtime transcription at audio boundary
- [Docs] Add Simplified Chinese translation (README.zh.md)
- [Bug]: Qwen3.8-Flash-Next: greedy decoding is non-deterministic from persistent_topk in prefill when prompt length nears indexer_budget (sm121/GB10)
- [Model][LoRA] Enable tower and connector LoRA for Isaac
- [Bugfix] DeepSeek-V3.2: render tools after the system prompt
- [Kernel] Add fused MoE Triton configs for Qwen1.5-MoE on RTX 4090 (E=30,N=1408 EP / E=60,N=704 TP)
- [Perf][Spec Decode] Avoid strided-view D2H stall on dynamic-K draft token copy
- [Model] Cohere Transcribe fails to initialize on Turing (fp16): expected scalar type Float but found Half in RelPositionMultiHeadAttention
- [Bug]: DeepSeek V4 DSpark TP=2 on 2× GB10 hits dual-rank Xid 31 at the inferred T=16 PIECEWISE warmup
- Docs
- Python not yet supported