Pinned Loading
Repositories
Showing 10 of 13 repositories
- flash-bidirectional-linear-attention Public
Triton implement of bi-directional (non-causal) linear attention
- native-sparse-attention Public
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
- hybrid-distillation Public
- distillation-fla Public Forked from OpenSparseLLMs/Linearization
Distillation pipeline from pretrained Transformers to customized FLA models
- vllm Public Forked from vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Top languages
Loading…
Most used topics
Loading…