EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

ggml : implement set_rows with i32 index (#16159)

Browse Source 
* implement set_rows with i32 index

* template fix

* test quantized path

warnings--

* Apply suggestions from code review

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

* forgotten name change

* deduplicate cuda/sycl and test-fix

* indent++

* vulkan: support set_rows with i32 index type (#16162)

* disable i32 index for webgpu for now

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
This commit is contained in:
Sigbjørn Skjæret
2025-09-22 19:13:00 +02:00
committed by GitHub
parent 432cf4304c
commit 3ecb2f671a
17 changed files with 299 additions and 133 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-metal/ggml-metal-device.cpp
View File

@@ -142,11 +142,11 @@ ggml_metal_pipeline_t ggml_metal_library_get_pipeline_get_rows(ggml_metal_librar
return res;
}
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_set_rows(ggml_metal_library_t lib, ggml_type tdst) {
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_set_rows(ggml_metal_library_t lib, ggml_type tidx, ggml_type tdst) {
char base[256];
char name[256];
snprintf(base, 256, "kernel_set_rows_%s", ggml_type_name(tdst));
snprintf(base, 256, "kernel_set_rows_%s_%s", ggml_type_name(tdst), ggml_type_name(tidx));
snprintf(name, 256, "%s", base);
ggml_metal_pipeline_t res = ggml_metal_library_get_pipeline(lib, name);