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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Handle E8M0 block scales in CUTLASS and Triton FP8 linear kernels
- [Bug]: SM120 CUTLASS blockwise FP8 GEMM rejects N % 128 != 0 (Invalid status; kv_a_proj N=576 in DeepSeek shapes)
- [RFC][Frontend/CLI]: Offline prefix-cache workload analyzer
- [ROCm][CI] Fix failing ROCm quick reduce test
- [Bugfix] Do not re-apply q/k/v scales on FlashInfer TRTLLM BF16-Q paths
- [Bugfix] Support non-gated MoE in online quantization and Marlin MoE tile padding
- VLLM_ENGINE_READY_TIMEOUT_S default (600s) insufficient for large MoE + cold FlashInfer JIT cache on new GPU archs (GB10 / sm_121a)
- [RFC]: PyTorch vLLM correctness audit
- [Bugfix] test_batch_inference_correctness now uses batch invariance
- [DSv4] Remove sparse-MLA q-head padding for FlashInfer >=0.6.14
- Docs
- Python not yet supported