llama : reorganize source code + improve CMake (#8006)

* scripts : update sync [no ci]

* files : relocate [no ci]

* ci : disable kompute build [no ci]

* cmake : fixes [no ci]

* server : fix mingw build

ggml-ci

* cmake : minor [no ci]

* cmake : link math library [no ci]

* cmake : build normal ggml library (not object library) [no ci]

* cmake : fix kompute build

ggml-ci

* make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE

ggml-ci

* move public backend headers to the public include directory (#8122)

* move public backend headers to the public include directory

* nix test

* spm : fix metal header

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* scripts : fix sync paths [no ci]

* scripts : sync ggml-blas.h [no ci]

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov
2024-06-26 18:33:02 +03:00
committed by GitHub
parent 8854044561
commit f3f65429c4
345 changed files with 2555 additions and 1937 deletions

View File

@@ -0,0 +1,32 @@
#version 450
#include "dequant_head.comp"
layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
layout (binding = 0) readonly buffer A {block_q4_0 data_a[];};
layout (binding = 1) writeonly buffer D {D_TYPE data_b[];};
void main() {
const uint i = gl_WorkGroupID.x * 4 + gl_LocalInvocationID.x / 64;
const uint tid = gl_LocalInvocationID.x % 64;
const uint il = tid/32;
const uint ir = tid%32;
const uint ib = 32*i + ir;
if (ib >= p.nel / 32) {
return;
}
const uint b_idx = 1024*i + 32*ir + 8*il;
const float d = float(data_a[ib].d);
const float dm = -8.0f * d;
const uint q_idx = 8*il;
[[unroll]] for (uint l = 0; l < 8; ++l) {
data_b[b_idx + l + 0] = D_TYPE(d * (data_a[ib].qs[q_idx + l] & 0xF) + dm);
data_b[b_idx + l + 16] = D_TYPE(d * (data_a[ib].qs[q_idx + l] >> 4) + dm);
}
}