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
- [RFC]: Shared JSON Schema structure for structured-output checks and transformations
- [Bugfix] Mark tool_result is_error in Anthropic converter
- [Docs] Document DP-aware routing with vLLM Router in the DP deployment guide
- [Platform] Add supports_v2_model_runner capability for out-of-tree platforms
- [Core][Logging] Add log_color and log_stream to LoggingConfig
- [Bug]: DeepSeek-V4-Flash + DFlash speculator fails at startup (fp8_ds_mla draft KV dtype; 16384 vs 4096 hidden states)
- [Bugfix][Metrics] Account for speculative decode tokens
- [Bugfix][Distributed] MergedColumnParallelLinear TP Rank Sync, Scale Parameter Sharding, and Bounded Multi-Threaded Loader
- [Bugfix][Quantization] FP8 Dynamic Block Size Auto-Discovery and Quark Prefix Normalization
- [Bugfix][ROCm] DeepSeek-V4/V4.1: Hybrid FP8/MXFP4 Quant Routing Guard, Fused Shared Experts, Engram Scale Translation, and VLM Generator Streaming
- Docs
- Python not yet supported