CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml webgpu: profiling, CI updates, reworking of command submission (#16452)

Browse Source 
* 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:
Reese Levine
2025-10-07 13:48:56 -07:00
committed by GitHub
parent aeaf8a36f0
commit 74b8fc17f9
6 changed files with 518 additions and 250 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/CMakeLists.txt
View File

@@ -222,6 +222,9 @@ option(GGML_VULKAN_VALIDATE "ggml: enable Vulkan validation"
option(GGML_VULKAN_RUN_TESTS "ggml: run Vulkan tests" OFF)
option(GGML_WEBGPU "ggml: use WebGPU" OFF)
option(GGML_WEBGPU_DEBUG "ggml: enable WebGPU debug output" OFF)
option(GGML_WEBGPU_CPU_PROFILE "ggml: enable WebGPU profiling (CPU)" OFF)
option(GGML_WEBGPU_GPU_PROFILE "ggml: enable WebGPU profiling (GPU)" OFF)
option(GGML_ZDNN "ggml: use zDNN" OFF)
option(GGML_METAL "ggml: use Metal" ${GGML_METAL_DEFAULT})
option(GGML_METAL_NDEBUG "ggml: disable Metal debugging" OFF)

8
ggml/src/ggml-webgpu/CMakeLists.txt
View File

@@ -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})

720
ggml/src/ggml-webgpu/ggml-webgpu.cpp
View File

File diff suppressed because it is too large Load Diff

2
ggml/src/ggml-webgpu/wgsl-shaders/mul_mat.tmpl.wgsl
View File

@@ -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) {