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
- [Bugfix][Benchmark] Fix bench throughput crash with BlazeEdit HF datasets
- [Bug]: VLLM_BATCH_INVARIANT=1 is not batch-invariant for Gemma-2-9B on H100 (FlashAttention sliding-window path under CUDA graphs)
- [Perf][Startup] Don't import vllm.parser from vllm.v1.structured_output
- [Perf][Startup] Compile per_block_cast_to_fp8 on first use
- [ROCm][DSv4.1] Share Engram host tables across DP ranks with HIP VMM
- [XPU][UT] Patch stream-capture check in SM90 sparse MLA plan test
- [Frontend] Add generative box answers for multimodal models on /v1/systemone
- [Perf][Model] Shard large QSA prefill query rows on SM90 TP4/TP8
- [Doc] Add 2x RTX 3090 (Ampere, sm86) AWQ INT4 recipe for Qwen3.8-27B
- [KV Transfer] Integrate layerwise transfer into MooncakeConnector
- Docs
- Python not yet supported