mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
ggml webgpu: profiling, CI updates, reworking of command submission (#16452)
* Add profiling * More detailed profiling * Rework command submission to avoid global locks * Update wait handling * try new method of waiting on futures * Add serializing of command submission in some cases * Add new pool for timestamp queries and clean up logging * Serialize command submission in CI and leave a TODO note * Update webgpu CI * Add myself as WebGPU codeowner * Deadlock avoidance * Leave WebGPU/Vulkan CI serialized * Fix divide by 0 * Fix logic in division by inflight_threads * Update CODEOWNERS and remove serialize submit option
This commit is contained in:
@@ -50,5 +50,13 @@ if (GGML_WEBGPU_DEBUG)
|
||||
target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_DEBUG=1)
|
||||
endif()
|
||||
|
||||
if (GGML_WEBGPU_CPU_PROFILE)
|
||||
target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_CPU_PROFILE=1)
|
||||
endif()
|
||||
|
||||
if (GGML_WEBGPU_GPU_PROFILE)
|
||||
target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_GPU_PROFILE=1)
|
||||
endif()
|
||||
|
||||
target_include_directories(ggml-webgpu PRIVATE ${SHADER_OUTPUT_DIR})
|
||||
target_link_libraries(ggml-webgpu PRIVATE ${DawnWebGPU_TARGET})
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -870,7 +870,7 @@ struct MulMatParams {
|
||||
|
||||
@group(0) @binding(3) var<uniform> params: MulMatParams;
|
||||
|
||||
@compute @workgroup_size(64)
|
||||
@compute @workgroup_size(256)
|
||||
fn main(@builtin(global_invocation_id) global_id: vec3<u32>) {
|
||||
let total = params.m * params.n * params.bs02 * params.broadcast2 * params.bs03 * params.broadcast3;
|
||||
if (global_id.x >= total) {
|
||||
|
||||
Reference in New Issue
Block a user