Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml-webgpu: add Q1_0 support (#22374)

Browse Source 
* add fast matmul matvec q1_0 kernel

* ggml-webgpu: drop redundant zero-fills in Q1_0 shmem init
This commit is contained in:
Rithik Sharma
2026-04-27 15:50:59 -07:00
committed by GitHub
parent 983ca8992e
commit 434b2a1ff6
5 changed files with 94 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
+7 -2
View File
@@ -1287,6 +1287,7 @@ class ggml_webgpu_shader_lib {
std::transform(type_upper.begin(), type_upper.end(), type_upper.begin(), ::toupper);
switch (key.src_type) {
case GGML_TYPE_Q1_0:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q5_0:
case GGML_TYPE_Q8_0:
@@ -1323,7 +1324,9 @@ class ggml_webgpu_shader_lib {
defines.push_back("DST_TYPE=f32");
if ((key.src_type >= GGML_TYPE_Q4_0 && key.src_type <= GGML_TYPE_Q8_1) ||
if (key.src_type == GGML_TYPE_Q1_0) {
defines.push_back("BLOCK_SIZE=128u");
} else if ((key.src_type >= GGML_TYPE_Q4_0 && key.src_type <= GGML_TYPE_Q8_1) ||
key.src_type == GGML_TYPE_IQ4_NL) {
defines.push_back("BLOCK_SIZE=32u");
} else if (key.src_type >= GGML_TYPE_Q2_K) {
@@ -1657,7 +1660,9 @@ class ggml_webgpu_shader_lib {
uint32_t wg_size = WEBGPU_MUL_MAT_VEC_WG_SIZE;
uint32_t outputs_per_wg = WEBGPU_MUL_MAT_VEC_FLOAT_OUTPUTS_PER_WG;
if (key.src0_type >= GGML_TYPE_Q2_K) {
if (key.src0_type == GGML_TYPE_Q1_0) {
outputs_per_wg = WEBGPU_MUL_MAT_VEC_LEGACY_Q_OUTPUTS_PER_WG;
} else if (key.src0_type >= GGML_TYPE_Q2_K) {
outputs_per_wg = WEBGPU_MUL_MAT_VEC_K_Q_OUTPUTS_PER_WG;
} else if (key.src0_type >= GGML_TYPE_Q4_0) {
outputs_per_wg = WEBGPU_MUL_MAT_VEC_LEGACY_Q_OUTPUTS_PER_WG;