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

ggml-webgpu: Add supports for DIAG and TRI (#20664)

Browse Source 
* Add supports for DIAG and TRI.

* Remove extra ttype and add a comment for TRI op.
This commit is contained in:
Masashi Yoshimura
2026-03-18 21:08:35 -07:00
committed by GitHub
parent 07ba6d275b
commit ea01d196d7
5 changed files with 77 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
+32 -5
View File
@@ -244,13 +244,15 @@ struct ggml_webgpu_binary_pipeline_key_hash {
/** Unary **/
struct ggml_webgpu_unary_pipeline_key {
int type;
int op;
bool is_unary; // many unary operators fall under the GGML_OP_UNARY umbrella
bool inplace;
int type;
int op;
bool is_unary; // many unary operators fall under the GGML_OP_UNARY umbrella
bool inplace;
ggml_tri_type ttype; // only used for GGML_OP_TRI
bool operator==(const ggml_webgpu_unary_pipeline_key & other) const {
return type == other.type && op == other.op && is_unary == other.is_unary && inplace == other.inplace;
return type == other.type && op == other.op && is_unary == other.is_unary && inplace == other.inplace &&
ttype == other.ttype;
}
};
@@ -261,6 +263,7 @@ struct ggml_webgpu_unary_pipeline_key_hash {
ggml_webgpu_hash_combine(seed, key.op);
ggml_webgpu_hash_combine(seed, key.is_unary);
ggml_webgpu_hash_combine(seed, key.inplace);
ggml_webgpu_hash_combine(seed, key.ttype);
return seed;
}
};
@@ -1058,6 +1061,7 @@ class ggml_webgpu_shader_lib {
.op = op,
.is_unary = is_unary,
.inplace = context.inplace,
.ttype = (ggml_tri_type) ggml_get_op_params_i32(context.dst, 0),
};
auto it = unary_pipelines.find(key);
@@ -1088,6 +1092,29 @@ class ggml_webgpu_shader_lib {
variant += "_inplace";
}
if (op == GGML_OP_TRI) {
switch (key.ttype) {
case GGML_TRI_TYPE_LOWER:
defines.push_back("TRI_TYPE_LOWER");
variant += "_tri_type_lower";
break;
case GGML_TRI_TYPE_LOWER_DIAG:
defines.push_back("TRI_TYPE_LOWER_DIAG");
variant += "_tri_type_lower_diag";
break;
case GGML_TRI_TYPE_UPPER:
defines.push_back("TRI_TYPE_UPPER");
variant += "_tri_type_upper";
break;
case GGML_TRI_TYPE_UPPER_DIAG:
defines.push_back("TRI_TYPE_UPPER_DIAG");
variant += "_tri_upper_diag";
break;
default:
GGML_ABORT("Unsupported ggml_tri_type for unary shader");
}
}
defines.push_back(std::string("WG_SIZE=") + std::to_string(context.max_wg_size));
auto processed = preprocessor.preprocess(wgsl_unary, defines);