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
- [Misc]: Random Output Generation with mistralai/Mixtral-8x22B-v0.1
- [Feature]: Is there any plan to support Cross-Layer Attention (CLA) ?
- [Bugfix][Kernel] Reduce GPU L1 cache pressure for act_order and tensor_parallel on smaller GPUs
- [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]: VllmWorkerProcess does not exit correctly when TP > 1
- [Bug]: benchmark_throughput gets TypeError: XFormersMetadata.__init__() got an unexpected keyword argument 'is_prompt' wit CPU
- [Usage]: low GPU usage in qwen1.5 110b int4 inference
- [Feature]: Set tensor_parallel_size to -1, to use all available cuda devices
- [Bug]: RuntimeError: "cat_cuda" not implemented for 'Float8_e4m3fn'
- [Bug]: Load LoRA adaptor for Llama3 seems not working
- Docs
- Python not yet supported