• 1
• 0
• 0

大师兄/pbs-attn

• 1
• 0
• 0

大师兄/MInference

[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while maintaining accuracy.

• 1
• 0
• 0

大师兄/Sparse-VideoGen

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

• 1
• 0
• 0

大师兄/spdlog

• 1
• 0
• 0

大师兄/pybind11

• 1
• 0
• 0

大师兄/composable_kernel

• 1
• 0
• 0

大师兄/pypatoh

• 1
• 0
• 0

大师兄/apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

• 1
• 0
• 0

大师兄/InternEvo

• 1
• 0
• 0

大师兄/Megatron-LM-chenyu

• 1
• 0
• 0

大师兄/cutlass

CUDA Templates and Python DSLs for High-Performance Linear Algebra

• 1
• 0
• 0

大师兄/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

• 1
• 0
• 0

大师兄/wv