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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [CI][AMD][BugFix] Prevent triton compiler error when running test_moe_layer with use_ep = True on ROCm
- [LoRA] Initial EP support for LoRA
- [NIXL] Support heterogeneous split_k_and_v policies for NIXL workers
- feat: Integrate vLLM with Weight Propagation Interface (WPI) for Zero-Copy Weight Transfer
- Revert "[Bugfix][MoE] Unpad routed output before shared expert add [Fixes #35949]" (#40794)
- [Core] Add dynamo_timed tracing for compilation startup
- [Core] Add dynamo_timed tracing for print_readable
- [NIXL][TURBOQUANT] Support turboquant in NIXL KV connector
- [Kernels] Integration for DeepGEMM MegaMoE kernel
- [Feature] Support a node-local external DP mode with a single vllm serve and aggregated admin health endpoint
- Docs
- Python not yet supported