mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 02:44:36 +00:00
a07d0fee1f
* ggml: aarch64: implement smmla kernel for q8_0_q8_0 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q8_0_q8_0 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: aarch64: implement smmla kernel for q4_0_q8_0 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q4_0_q8_0 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: aarch64: implement smmla kernel for q4_1_q8_1 quantized gemm armv8.2-a and above supports MMLA instructions that have higher throughput than DOT. this commit adds mmla kernel for q4_1_q8_1 gemm. The feature is enabled if the platform supports "__ARM_FEATURE_MATMUL_INT8" On AWS Graviton3 processors this kernel resulted up to 1.5x improvement for prompt evaluation throughput compared to the default sdot kernel. * ggml: update unit tests for the new vec_dot interface * llama.cpp: add MATMUL_INT8 capability to system_info |
||
|---|---|---|
| .. | ||
| base64.hpp | ||
| build-info.cpp.in | ||
| CMakeLists.txt | ||
| common.cpp | ||
| common.h | ||
| console.cpp | ||
| console.h | ||
| grammar-parser.cpp | ||
| grammar-parser.h | ||
| log.h | ||
| sampling.cpp | ||
| sampling.h | ||
| stb_image.h | ||
| train.cpp | ||
| train.h | ||