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
- [Feature][SP] Support Sequence Parallelism for Multimodal Encoder
- [Frontend] Add `/v1/messages/render` endpoint for the Anthropic Messages API
- [PD][Core] Add partial prefix caching for hybrid model in PD disaggregation
- [Bug]: MoE Detection Logic Fails for Non-Language Multimodal Models
- [Feature][Observability][Frontend]: Propagate OpenTelemetry Spans to IOProcessor for Custom Sub-Span Creation
- [Misc] Add unit test for fused_moe_kernel_gptq_awq MoE kernel
- [Kernel][XPU] Use Triton tensor descriptor for dt_out store in chunk_cumsum
- [Bugfix] Handle FileNotFoundError in reasoning_config.initialize_toke…
- [Feature] Add batch invariance support to GDN_ATTN backend
- [Refactor] Make Int8ScaledMMLinearLayerConfig use QuantKey
- Docs
- Python not yet supported