Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 17:25:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	ci/run.sh
#	docs/function-calling.md
#	examples/gritlm/gritlm.cpp
#	ggml/CMakeLists.txt
#	ggml/cmake/common.cmake
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/ggml-cpu.c
#	ggml/src/ggml-hip/CMakeLists.txt
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	ggml/src/ggml-vulkan/vulkan-shaders/CMakeLists.txt
#	requirements/requirements-compare-llama-bench.txt
#	scripts/compare-llama-bench.py
#	tests/CMakeLists.txt
This commit is contained in:
Concedo
2025-06-18 00:16:54 +08:00
parent f07434f4c1 860a9e4eef
commit 4356a00f4a
47 changed files with 1526 additions and 301 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/repack.cpp
+2 -13
View File
@@ -8,6 +8,8 @@
#include "ggml-cpu-impl.h"
#include "traits.h"
#include "arch-fallback.h"
#include <cmath>
#include <cstring>
#include <cassert>
@@ -83,7 +85,6 @@ void ggml_quantize_mat_q8_0_4x4_generic(const float * GGML_RESTRICT x, void * GG
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_quantize_mat_q8_0_4x4)
void ggml_quantize_mat_q8_0_4x8_generic(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k) {
assert(QK8_0 == 32);
@@ -122,7 +123,6 @@ void ggml_quantize_mat_q8_0_4x8_generic(const float * GGML_RESTRICT x, void * GG
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_quantize_mat_q8_0_4x8)
void ggml_quantize_mat_q8_K_4x8_generic(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k) {
assert(QK_K == 256);
@@ -174,7 +174,6 @@ void ggml_quantize_mat_q8_K_4x8_generic(const float * GGML_RESTRICT x, void * GG
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_quantize_mat_q8_K_4x8)
} // extern "C"
@@ -244,7 +243,6 @@ void ggml_gemv_q4_0_4x4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs,
for (int j = 0; j < ncols_interleaved; j++) s[x * ncols_interleaved + j] = sumf[j];
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemv_q4_0_4x4_q8_0)
void ggml_gemv_q4_0_4x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK8_0;
@@ -289,7 +287,6 @@ void ggml_gemv_q4_0_4x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs,
for (int j = 0; j < ncols_interleaved; j++) s[x * ncols_interleaved + j] = sumf[j];
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemv_q4_0_4x8_q8_0)
void ggml_gemv_q4_0_8x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK8_0;
@@ -336,7 +333,6 @@ void ggml_gemv_q4_0_8x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs,
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemv_q4_0_8x8_q8_0)
void ggml_gemv_q4_K_8x8_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK_K;
@@ -415,7 +411,6 @@ void ggml_gemv_q4_K_8x8_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs,
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemv_q4_K_8x8_q8_K)
void ggml_gemv_iq4_nl_4x4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK8_0;
@@ -462,7 +457,6 @@ void ggml_gemv_iq4_nl_4x4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemv_iq4_nl_4x4_q8_0)
void ggml_gemm_q4_0_4x4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK8_0;
@@ -519,7 +513,6 @@ void ggml_gemm_q4_0_4x4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs,
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemm_q4_0_4x4_q8_0)
void ggml_gemm_q4_0_4x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK8_0;
@@ -574,7 +567,6 @@ void ggml_gemm_q4_0_4x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs,
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemm_q4_0_4x8_q8_0)
void ggml_gemm_q4_0_8x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK8_0;
@@ -629,7 +621,6 @@ void ggml_gemm_q4_0_8x8_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs,
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemm_q4_0_8x8_q8_0)
void ggml_gemm_q4_K_8x8_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK_K;
@@ -719,7 +710,6 @@ void ggml_gemm_q4_K_8x8_q8_K_generic(int n, float * GGML_RESTRICT s, size_t bs,
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemm_q4_K_8x8_q8_K)
void ggml_gemm_iq4_nl_4x4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, const void * GGML_RESTRICT vy, int nr, int nc) {
const int qk = QK8_0;
@@ -776,7 +766,6 @@ void ggml_gemm_iq4_nl_4x4_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs
}
}
}
GGML_CPU_NATIVE_IMPL(ggml_gemm_iq4_nl_4x4_q8_0)
} // extern "C"