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 supported59 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] Add per-phase linear activation precision to quantization_config
- [Benchmark][KV Offload] Add multi-turn KV offloading benchmark script
- [hw-agnostic] Linear layers for the Transformers backend
- [Perf][KV Offload] Bound copy descriptors submitted per step for CPU->GPU loads
- [Perf][mHC] use FlashInfer mega mHC for MHCFusedPostPreOp (GLM-5.3-Fl…
- [Rust][Benchmark] Align vllm-bench result files and requests with Python
- [KVConnector] Enable LMCache MP connector for the extensible kv cache
- [Bugfix][Quantization] Respect non-gated shard count in FP4 Marlin
- [Perf][GDN] Export Triton prefill checkpoints into the paged state cache
- [ROCm][Perf] Qwen3.8-Flash-Next specialized decode at 1-128 rows on MI355X (--monokernel)
- Docs
- Python not yet supported