vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml : add Q5_0 and Q5_1 quantization (#1187)

Browse source 
* ggml : add Q5_0 quantization (cuBLAS only)

* ggml : fix Q5_0 qh -> uint32_t

* ggml : fix q5_0 histogram stats

* ggml : q5_0 scalar dot product

* ggml : q5_0 ARM NEON dot

* ggml : q5_0 more efficient ARM NEON using uint64_t masks

* ggml : rename Q5_0 -> Q5_1

* ggml : adding Q5_0 mode

* quantize : add Q5_0 and Q5_1 to map

* ggml : AVX2 optimizations for Q5_0, Q5_1 (#1195)

---------

Co-authored-by: Stephan Walter <stephan@walter.name>
This commit is contained in:
Georgi Gerganov 2023-04-26 23:14:13 +03:00 • committed by GitHub
parent 87a6f846d3
commit 574406dc7e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 711 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

85
ggml-cuda.cu
View file

@ -37,6 +37,23 @@ typedef struct {
} block_q4_3;
static_assert(sizeof(block_q4_3) == 2 * sizeof(ggml_fp16_t) + QK4_3 / 2, "wrong q4_3 block size/padding");
#define QK5_0 32
typedef struct {
__half d; // delta
uint8_t qh[4]; // 5-th bit of quants
uint8_t qs[QK5_0 / 2]; // nibbles / quants
} block_q5_0;
static_assert(sizeof(block_q5_0) == sizeof(ggml_fp16_t) + sizeof(uint32_t) + QK5_0 / 2, "wrong q5_0 block size/padding");
#define QK5_1 32
typedef struct {
__half d; // delta
__half m; // min
uint32_t qh; // 5-th bit of quants
uint8_t qs[QK5_1 / 2]; // nibbles / quants
} block_q5_1;
static_assert(sizeof(block_q5_1) == 2 * sizeof(ggml_fp16_t) + sizeof(uint32_t) + QK5_1 / 2, "wrong q5_1 block size/padding");
#define QK8_0 32
typedef struct {
float d; // delta
@ -138,6 +155,64 @@ static __global__ void dequantize_block_q4_3(const void * vx, float * y) {
}
}
static __global__ void dequantize_block_q5_0(const void * vx, float * y) {
const block_q5_0 * x = (const block_q5_0 *) vx;
const int i = blockIdx.x;
const float d = x[i].d;
const uint8_t * pp = x[i].qs;
uint32_t qh;
memcpy(&qh, x[i].qh, sizeof(qh));
for (int l = 0; l < QK5_0; l += 2) {
const uint8_t vi = pp[l/2];
const int8_t vh0 = ((qh & (1 << (l + 0))) >> (l + 0)) << 4;
const int8_t vh1 = ((qh & (1 << (l + 1))) >> (l + 1)) << 4;
const int8_t vi0 = ((vi & 0xf) | vh0);
const int8_t vi1 = ((vi >> 4) | vh1);
const float v0 = (vi0 - 16)*d;
const float v1 = (vi1 - 16)*d;
y[i*QK5_0 + l + 0] = v0;
y[i*QK5_0 + l + 1] = v1;
}
}
static __global__ void dequantize_block_q5_1(const void * vx, float * y) {
const block_q5_1 * x = (const block_q5_1 *) vx;
const int i = blockIdx.x;
const float d = x[i].d;
const float m = x[i].m;
const uint8_t * pp = x[i].qs;
const uint32_t qh = x[i].qh;
for (int l = 0; l < QK5_1; l += 2) {
const uint8_t vi = pp[l/2];
const int8_t vh0 = ((qh & (1 << (l + 0))) >> (l + 0)) << 4;
const int8_t vh1 = ((qh & (1 << (l + 1))) >> (l + 1)) << 4;
const int8_t vi0 = (vi & 0xf) | vh0;
const int8_t vi1 = (vi >> 4) | vh1;
const float v0 = vi0*d + m;
const float v1 = vi1*d + m;
y[i*QK5_1 + l + 0] = v0;
y[i*QK5_1 + l + 1] = v1;
}
}
static __global__ void dequantize_block_q8_0(const void * vx, float * y) {
const block_q8_0 * x = (const block_q8_0 *) vx;
@ -174,6 +249,16 @@ void dequantize_row_q4_3_cuda(const void * vx, float * y, int k, cudaStream_t st
dequantize_block_q4_3<<<nb, 1, 0, stream>>>(vx, y);
}
void dequantize_row_q5_0_cuda(const void * vx, float * y, int k, cudaStream_t stream) {
const int nb = k / QK5_0;
dequantize_block_q5_0<<<nb, 1, 0, stream>>>(vx, y);
}
void dequantize_row_q5_1_cuda(const void * vx, float * y, int k, cudaStream_t stream) {
const int nb = k / QK5_1;
dequantize_block_q5_1<<<nb, 1, 0, stream>>>(vx, y);
}
void dequantize_row_q8_0_cuda(const void * vx, float * y, int k, cudaStream_t stream) {
const int nb = k / QK8_0;
dequantize_block_q8_0<<<nb, 1, 0, stream>>>(vx, y);