ik_llama.cpp.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Collapse)	Author
2024-02-11	ggml : add mmla kernels for quantized GEMM (#4966)	snadampal
	* 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
2023-09-28	build : enable more non-default compiler warnings (#3200)	Cebtenzzre

2023-07-05	ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)	Stephan Walter
	* Generalize quantize_fns for simpler FP16 handling * Remove call to ggml_cuda_mul_mat_get_wsize * ci : disable FMA for mac os actions --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-04-21	ggml : a faster version for Q4_1 x Q8_0 dot products (#1083)	Kawrakow
	* A faster version for Q4_1 x Q8_0 dot products The idea nehind being that Q8_0 quantized values get used many times in the matrix multiplications where they are involved. In the current implementations, when we are evaluating the dot products, we need to compute the sum of the quants in the Q8_0 vector, so the same operation is repeated many times. Here we pre-compute the sum during Q8_0 quantization, store it in the now modified block_q8_0 struct, and then reuse this result in the subsequent dot products. In a synthetic benchmark (just compute a bunch of dot products), this change speeds up the Q4_1 * Q8_0 dot product by 80%, making the performance identical to Q4_0 * Q8_0. In practical application, I see a ~15% gain in speed for token prediction on M2, and ~5% gain on Ryzen 7950X. The speed gain in the prompt evaluation is much bigger (around 50%). I have only done the change for the scalar version, ARM_NEON, and AVX2, so we still need an AVX implementation. * Cleaning up --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>