FireAttention V3: Enabling AMD as a Viable Alternative for GPU Inference
FireAttention on AMD delivers state-of-the-art results
Meta's Llama 3.2 models—1B, 3B, 11B, and 90B - available now. Read more
FireAttention on AMD delivers state-of-the-art results
9/25/2024
View Article9/25/2024
View Article9/18/2024
View Article8/30/2024
View Article8/29/2024
View Article8/14/2024
View Article8/1/2024
View Article7/23/2024
View Article7/11/2024
View Article6/23/2024
View Article6/20/2024
View Article6/17/2024
View Article6/3/2024
View Article6/3/2024
View Article5/8/2024
View Article5/6/2024
View Article4/18/2024
View Article4/17/2024
View Article3/21/2024
View Article3/8/2024
View Article3/1/2024
View Article2/20/2024
View Article2/20/2024
View Article1/18/2024
View Article1/8/2024
View Article12/20/2023
View Article12/14/2023
View Article11/3/2023
View Article11/2/2023
View Article10/27/2023
View Article10/11/2023
View Article10/2/2023
View Article9/12/2023
View Article8/29/2023
View Article8/17/2023
View Article7/12/2023
View Article