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
- [Usage]: What's the minimum VRAM needed to use entire context length for Llama 3.1 70B and 405B
- [Feature]: RuntimeError: FlashAttention only supports Ampere GPUs or newer.
- [New Model]: DiT
- [New Model]: Support for allenai/OLMoE-1B-7B-0924
- [Installation]: error: can't copy 'build/lib.linux-x86_64-3.10/vllm/_core_C.abi3.so': doesn't exist or not a regular file
- [Usage]: "RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)`" when serving w8a8
- [Usage]: number of allocated GPU blocks depending on max_seq_length ??
- [Usage]: how to release cuda memory
- [Bug]: In v0.6.0 and above, Some of monitoring metrics are not correct.
- [Benchmark] Add block_size option to benchmark_throughput.py
- Docs
- Python not yet supported