FlashAttention

6 posts · 3 sources

CoreweaveBlog1w

ART-Optimized Megatron (AOM): 12x higher training throughput

Together AIBlog15 Jul

Together AI brings Thinking Machines Lab’s new model Inkling on day 0

ModalBlog11 Jun

Making FlashAttention-4 faster for inference

Together AIBlog1 Apr

Inside the Together AI kernels team

Together AIBlog5 Mar

FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling

Together AIBlog5 Mar

Key research and product announcements at the AI Native Conf