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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Request for Ascend NPU support
- [Feature]: FlashAttention 3 support
- [core] Sampling controller interface
- [Feature]: Multi-Proposers support for speculative decoding.
- [Bug]: deepseek-coder-v2-lite-instruct; Exception in worker VllmWorkerProcess while processing method initialize_cache: [Errno 2] No such file or directory: '/root/.triton/cache/de758c429c9ff1f18930bbd9c3004506/fused_moe_kernel.json.tmp.pid_1528_587007', Traceback (most recent call last):
- [Bug]: benchmark_throughput gets TypeError: XFormersMetadata.__init__() got an unexpected keyword argument 'is_prompt' wit CPU
- No executable after building vllm from source with CPU support
- [Core][Model] Add simple_model_runner and a new model XLMRobertaForSequenceClassification through multimodal interface
- [Feature]: FlashInfer + Gemma 2 for AMD GPU
- [Bug]: Gemma2 supports 8192 context with sliding window, but vllm only does 4196 or fails if try 8192
- Docs
- Python not yet supported