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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- feat: use safetensors prefetch api
- [Bugfix][MLA] Scope DSpark non-causal capability to builder layers
- [CI] Shard (H200 MIG 35GB / MI300) Entrypoints Integration (LLM) into whole coverage units
- [ROCm][Perf][GLM-5.3-Flash] "Fit kpool top-k indices to AITER" with a single Triton kernel
- [Bugfix] Exclude SM107 (Rubin) from support_deep_gemm()
- FlashInfer autotune for trtllm_fp4_block_scale_moe wedges forever on SM103 (GB300): trtllm_gemm cubin is sm_100a-only, no PTX, and the autotuner has no timeout
- [ROCm][Kimi-K3] Optimize low-concurrency speculative KDA
- [Mypy] Fix mypy typing for Qwen and Qianfan models
- [CI] Wire the 17 root-level tests/test_*.py into misc.yaml
- [Bugfix][ROCm] Drop -1 sentinels when building the ragged sparse-MLA indices
- Docs
- Python not yet supported