sleepy/llama.cpp
1
0
Fork 0
Code Issues 8 Pull Requests 1 Actions 175 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.cpp
+4
View File
@@ -1389,6 +1389,7 @@ static webgpu_encoded_op ggml_webgpu_mul_mat(webgpu_context & ctx,
case GGML_TYPE_Q5_K:
case GGML_TYPE_Q3_K:
case GGML_TYPE_Q2_K:
case GGML_TYPE_Q1_0:
use_fast = true;
break;
case GGML_TYPE_IQ1_S:
@@ -3736,6 +3737,7 @@ static bool ggml_backend_webgpu_device_supports_buft(ggml_backend_dev_t dev, ggm
static bool ggml_webgpu_supported_qtype(ggml_type type) {
switch (type) {
case GGML_TYPE_Q1_0:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q4_1:
case GGML_TYPE_Q5_0:
@@ -3830,6 +3832,7 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
switch (src0->type) {
case GGML_TYPE_F32:
case GGML_TYPE_F16:
case GGML_TYPE_Q1_0:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q4_1:
case GGML_TYPE_Q5_0:
@@ -3868,6 +3871,7 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
switch (src0->type) {
case GGML_TYPE_F32:
case GGML_TYPE_F16:
case GGML_TYPE_Q1_0:
case GGML_TYPE_Q4_0:
case GGML_TYPE_Q4_1:
case GGML_TYPE_Q5_0: