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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Sparse-indexer DCP top-k merge allocates (1 + 2 * dcp) * 8 * T * K bytes per step that the profile run never sees, OOM on the first long prefill
- [Bug]: CUDA graph memory estimate (#53306) reports 2.16 GiB against 1.19 GiB actually captured on GLM-5.3 TP4/DCP4: the profiling pass measures things the real capture does not, and the FULL extrapolation uses the second-largest graph as the per-graph cost
- [Bugfix][KV Connector] Stop P/D transfers short of the last prompt token
- [NIXL] Share in-flight prefix loads across requests
- [Perf][KV Connector] Drop the redundant index_select in kv_postprocess_layout_on_receive
- [KV Connector] Stop mutating the prefill payload after it has been sent
- [RFC]: Modular read strategies and custom parameters for /v1/systemone and /v1/decisions
- [RFC]: MoRIIO WRITE failure handling and safe KV block reclamation
- Fix suppress_stdout to target the real stdout fd
- [Bug] DeepSeek-V4.1-Flash cannot use TP > 8: Engram hash-head sharding assertion rejects tp_size=16 across 2 nodes
- Docs
- Python not yet supported