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 supported31 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Deprecate `kv_both` for NIXLConnector and Enforce Explicit P/D Roles
- [Bug]: Multinode no NVLink DEP8 server hangs in CUDA graph replay on MoE models during benchmarking
- Adding JSONDisk to Cache
- fix(chat_utils): coerce tool_call arguments "null" to {} (#43851)
- [DeepSeek V4] Fix wo_eos passthrough and continue_final_message support
- [Bugfix][V1][Spec Decode] Don't mutate M-RoPE state from draft-path _gather_mm_embeddings (#43820)
- [Kernel][ROCm] CDNA HIP attention kernels for INT8/INT4 per-token-head KV cache (MI300)
- fix: skip missing MultiConnector Prometheus metrics
- Fix data source selection in query_statistics.json
- [Doc] Clarify NIXL KV metrics aggregation semantics
- Docs
- Python not yet supported