jeejeelee/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
@Inferact | @vllm-project
Repositories
jeejeelee/flashinfer
FlashInfer: Kernel Library for LLM Serving
jeejeelee/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
jeejeelee/recipes
Common recipes to run vLLM
jeejeelee/DeepGEMM
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
jeejeelee/vllm-project.github.io
jeejeelee/DeepEP
DeepEP: an efficient expert-parallel communication library
jeejeelee/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
jeejeelee/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
jeejeelee/cutlass
CUDA Templates for Linear Algebra Subroutines