nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

hexagon: Q4_0 and MXFP4 repack fixes (#20527)

Browse Source 
* hexagon: fix tail corruption with rows sizes not multiple of 256

* hexagon: use different stride for repacking partial blocks

* hex-mm: update repack and kernels to avoid shuffles for full 256-element blocks

Previous commit changed the repacking to use even:odd (0:1,2:3,..) packing
instead of the original (0:128,1:129,...) packing in order to fix tail corruption.
Since the mm kernels already deal with partial tails we can use even:odd
packing only for the last block.
This avoid performance penalty of having to shuffle to zip the elements
in the common case.

* hex-mm: update rmpy x8 for better optimizations

* hex-mm: tighten supported MUL_MAT checks to avoid spurios failures

* hex-mm: use vzero to init accumulators

* hex-mm: properly call partial rmpy_x8
This commit is contained in:
Max Krasnyansky
2026-03-14 11:09:08 -07:00
committed by GitHub
parent 9f774e45ee
commit 609ea50026
2 changed files with 287 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-hexagon/ggml-hexagon.cpp
+34 -9
View File
@@ -402,6 +402,7 @@ static void pack_q4_0_quants(block_q4_0 * x, const uint8_t * qs, unsigned int bi
static void repack_row_q4x4x2(uint8_t * y, const block_q4_0 * x, int64_t k) {
static const int qk = QK_Q4_0x4x2;
const int nb = (k + qk - 1) / qk; // number of blocks (padded)
const int nloe = k % qk; // leftovers
const int dblk_size = 8 * 2; // 8x __fp16
const int qblk_size = qk / 2; // int4
@@ -435,9 +436,11 @@ static void repack_row_q4x4x2(uint8_t * y, const block_q4_0 * x, int64_t k) {
unpack_q4_0_quants(qs, &x[i * 8 + 6], 6);
unpack_q4_0_quants(qs, &x[i * 8 + 7], 7);
bool partial = (nloe && i == nb-1);
uint8_t * q = y_q + (i * qblk_size);
for (int j = 0; j < qk / 2; j++) {
q[j] = (qs[j + 128] << 4) | qs[j];
q[j] = partial ? (qs[j*2+1] << 4) | qs[j*2+0] : (qs[j+128] << 4) | qs[j+000];
}
}
@@ -467,6 +470,7 @@ static void repack_row_q4x4x2(uint8_t * y, const block_q4_0 * x, int64_t k) {
static void unpack_row_q4x4x2(block_q4_0 * x, const uint8_t * y, int64_t k) {
static const int qk = QK_Q4_0x4x2;
const int nb = (k + qk - 1) / qk; // number of blocks (padded)
const int nloe = k % qk; // leftovers
const int dblk_size = 8 * 2; // 8x __fp16
const int qblk_size = qk / 2; // int4
@@ -485,10 +489,17 @@ static void unpack_row_q4x4x2(block_q4_0 * x, const uint8_t * y, int64_t k) {
for (int i = 0; i < nb; i++) {
uint8_t qs[QK_Q4_0x4x2]; // unpacked quants
bool partial = (nloe && i == nb-1);
const uint8_t * q = y_q + (i * qblk_size);
for (int j = 0; j < qk / 2; j++) {
qs[j] = q[j] & 0xf;
qs[j + 128] = q[j] >> 4;
if (partial) {
qs[j*2+0] = q[j] & 0xf;
qs[j*2+1] = q[j] >> 4;
} else {
qs[j+000] = q[j] & 0xf;
qs[j+128] = q[j] >> 4;
}
}
pack_q4_0_quants(&x[i * 8 + 0], qs, 0);
@@ -1078,6 +1089,7 @@ static void pack_mxfp4_quants(block_mxfp4 * x, const uint8_t * qs, unsigned int
static void repack_row_mxfp4x4x2(uint8_t * y, const block_mxfp4 * x, int64_t k) {
static const int qk = QK_MXFP4x4x2;
const int nb = (k + qk - 1) / qk; // number of blocks (padded)
const int nloe = k % qk; // leftovers
const int eblk_size = 8 * 1; // 8x E8M0
const int qblk_size = qk / 2; // int4
@@ -1112,9 +1124,11 @@ static void repack_row_mxfp4x4x2(uint8_t * y, const block_mxfp4 * x, int64_t k)
unpack_mxfp4_quants(qs, &x[i * 8 + 6], 6);
unpack_mxfp4_quants(qs, &x[i * 8 + 7], 7);
bool partial = (nloe && i == nb-1);
uint8_t * q = y_q + (i * qblk_size);
for (int j = 0; j < qk / 2; j++) {
q[j] = (qs[j + 128] << 4) | qs[j];
q[j] = partial ? (qs[j*2+1] << 4) | qs[j*2+0] : (qs[j+128] << 4) | qs[j+000];
}
}
@@ -1144,6 +1158,7 @@ static void repack_row_mxfp4x4x2(uint8_t * y, const block_mxfp4 * x, int64_t k)
static void unpack_row_mxfp4x4x2(block_mxfp4 * x, const uint8_t * y, int64_t k) {
static const int qk = QK_MXFP4x4x2;
const int nb = (k + qk - 1) / qk; // number of blocks (padded)
const int nloe = k % qk; // leftovers
const int eblk_size = 8 * 1; // 8x E8M0
const int qblk_size = qk / 2; // int4
@@ -1162,10 +1177,17 @@ static void unpack_row_mxfp4x4x2(block_mxfp4 * x, const uint8_t * y, int64_t k)
for (int i = 0; i < nb; i++) {
uint8_t qs[QK_MXFP4x4x2]; // unpacked quants
bool partial = (nloe && i == nb-1);
const uint8_t * q = y_q + (i * qblk_size);
for (int j = 0; j < qk / 2; j++) {
qs[j] = q[j] & 0xf;
qs[j + 128] = q[j] >> 4;
if (partial) {
qs[j*2+0] = q[j] & 0xf;
qs[j*2+1] = q[j] >> 4;
} else {
qs[j+000] = q[j] & 0xf;
qs[j+128] = q[j] >> 4;
}
}
pack_mxfp4_quants(&x[i * 8 + 0], qs, 0);
@@ -1801,12 +1823,12 @@ static bool ggml_hexagon_supported_mul_mat(const struct ggml_hexagon_session * s
return false;
}
if (src0->ne[1] > 16 * 1024) {
if (ggml_nrows(src0) > 16 * 1024) {
return false; // typically the lm-head which would be too large for VTCM
}
if ((src1->ne[2] != 1 || src1->ne[3] != 1)) {
return false;
if (ggml_nrows(src1) > 1024 || src1->ne[2] != 1 || src1->ne[3] != 1) {
return false; // no huge batches or broadcasting (for now)
}
// src0 (weights) must be repacked
@@ -1820,6 +1842,9 @@ static bool ggml_hexagon_supported_mul_mat(const struct ggml_hexagon_session * s
GGML_LOG_DEBUG("ggml_hexagon_supported_mul_mat: permuted F16 src0 not supported\n");
return false;
}
if (ggml_nrows(src1) > 1024) {
return false; // no huge batches (for now)
}
break;
default: