Edward Chen 150c4cb8fe [MLAS AArch64] SQNBitGemm CompInt8 kernel (#18953) ... Implement ARM NEON SQNBitGemm kernel that first block quantizes A to int8 and then does int8 multiplication.		2024-01-12 17:58:08 -08:00
..
cpu	[MLAS AArch64] SQNBitGemm CompInt8 kernel (#18953)	2024-01-12 17:58:08 -08:00
cuda	add bfp16 to gqa (#19095)	2024-01-11 20:53:31 -08:00
js	[js/web] JSEP Attention & MultiHeadAttention (#17742)	2023-11-17 12:23:52 -08:00
rocm	[ROCm] do not use failed miopen fusion compile (#19012)	2024-01-08 19:06:45 +08:00