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
- [Docs][Model] Add Qwen2.5-Coder-1.5B-Instruct to batch invariance tested models
- [Perf] Lower FlashInfer CuTeDSL BF16 GEMM to aten mm above 32 tokens
- [Bugfix][KV Connector][NIXL] Support heterogeneous P/D TP for mixed MLA models
- [Bugfix] Reserve construction-time scratch across workspace slots
- [ROCm] Default AITER on for CDNA3+ when the package is installed
- Fix shutdown order: drain engines before stopping API servers with --api-server-count > 1
- [CPU][Bugfix] Respect expert map in unquantized MoE
- [Quantization][INC][XPU] Add online NVFP4 to AutoRound MXFP4 conversion
- [Performance]: Waiting requests re-walk their whole prefix-cache hit on every scheduling step
- [Bug]: enable_tower_connector_lora: get_mm_lora_token_counts() under-sizes punica wrappers in 8 models (startup/runtime token_lora_mapping asserts)
- Docs
- Python not yet supported