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
- [kernel][perf][minimax m3] adds flashinfer MSA backend for sm100
- [Bugfix][CI] Give cpu_test a gloo dist_init so it cannot poison forked engines
- [Perf][Marlin] Group full-K tiles for wide block-FP8 GEMMs on SM89
- [11/N][warmup][DSv4] Migrate Gumbel sampling kernel
- [Bugfix][QSA] Reuse bounded prefill logits workspace
- [ROCm] Fix fusion passes for AITER fp8 bpreshuffle blockscale GEMM
- [Bug]: activation override in test_flashinfer_cutedsl_fp4_moe silently tests RELU2 for every parametrize case
- [Doc]: ec_cpu_connector.md refers to a no-NIXL import test that doesn't exist
- [Test][EC Connector] Add the no-NIXL import test the docs refer to
- [Perf][Kimi-K3] Make GEMM-AR SM margin configurable
- Docs
- Python not yet supported