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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Multimodal] Let encoder-decoder plugins process text-only encoder prompts (T5Gemma 2)
- [Metrics] Add vllm:kv_admission_reserved_blocks gauge
- [ROCm] Bound DeepSeek V4 steady-state memory on gfx1151
- [Metrics] Add vllm:kv_token_slots gauge
- [Perf][ROCm] Split the top-k mask across programs for small batches
- [ROCm][Perf] Skip masked-out context tiles for sliding-window models in Triton prefix-prefill
- [ROCm][Kernel] Add AITER Triton MXFP8 linear kernel for CDNA4
- [Spec Decode] Consistent drafted, verified and accepted token counts
- [ROCm][Perf] Add direct FP8 kv_b_proj output for FlyDSL MLA prefill
- [Bugfix][Benchmark] Parse SSE data fields across streaming backends
- Docs
- Python not yet supported