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

ggml webgpu: add support for emscripten builds (#17184)

Browse Source 
* Faster tensors (#8)

Add fast matrix and matrix/vector multiplication.

* Use map for shader replacements instead of pair of strings

* Wasm (#9)

* webgpu : fix build on emscripten

* more debugging stuff

* test-backend-ops: force single thread on wasm

* fix single-thread case for init_tensor_uniform

* use jspi

* add pthread

* test: remember to set n_thread for cpu backend

* Add buffer label and enable dawn-specific toggles to turn off some checks

* Intermediate state

* Fast working f16/f32 vec4

* Working float fast mul mat

* Clean up naming of mul_mat to match logical model, start work on q mul_mat

* Setup for subgroup matrix mat mul

* Basic working subgroup matrix

* Working subgroup matrix tiling

* Handle weirder sg matrix sizes (but still % sg matrix size)

* Working start to gemv

* working f16 accumulation with shared memory staging

* Print out available subgroup matrix configurations

* Vectorize dst stores for sg matrix shader

* Gemv working scalar

* Minor set_rows optimization (#4)

* updated optimization, fixed errors

* non vectorized version now dispatches one thread per element

* Simplify

* Change logic for set_rows pipelines

---------

Co-authored-by: Neha Abbas <nehaabbas@macbookpro.lan>
Co-authored-by: Neha Abbas <nehaabbas@ReeseLevines-MacBook-Pro.local>
Co-authored-by: Reese Levine <reeselevine1@gmail.com>

* Comment on dawn toggles

* Working subgroup matrix code for (semi)generic sizes

* Remove some comments

* Cleanup code

* Update dawn version and move to portable subgroup size

* Try to fix new dawn release

* Update subgroup size comment

* Only check for subgroup matrix configs if they are supported

* Add toggles for subgroup matrix/f16 support on nvidia+vulkan

* Make row/col naming consistent

* Refactor shared memory loading

* Move sg matrix stores to correct file

* Working q4_0

* Formatting

* Work with emscripten builds

* Fix test-backend-ops emscripten for f16/quantized types

* Use emscripten memory64 to support get_memory

* Add build flags and try ci

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>

* Remove extra whitespace

* Move wasm single-thread logic out of test-backend-ops for cpu backend

* Disable multiple threads for emscripten single-thread builds in ggml_graph_plan

* Fix .gitignore

* Add memory64 option and remove unneeded macros for setting threads to 1

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Reese Levine
2025-12-03 10:25:34 +01:00
committed by GitHub
co-authored by Neha Abbas Neha Abbas Xuan Son Nguyen
parent b3e3060f4e
commit 7ca5991d2b
12 changed files with 355 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/CMakeLists.txt
+20 -2
View File
@@ -39,8 +39,23 @@ add_dependencies(ggml-webgpu generate_shaders)
if(EMSCRIPTEN)
set(EMDAWNWEBGPU_DIR "" CACHE PATH "Path to emdawnwebgpu_pkg")
target_compile_options(ggml-webgpu PRIVATE "--use-port=${EMDAWNWEBGPU_DIR}/emdawnwebgpu.port.py")
target_link_options(ggml-webgpu PRIVATE "--use-port=${EMDAWNWEBGPU_DIR}/emdawnwebgpu.port.py")
if(NOT EMDAWNWEBGPU_DIR)
# default built-in port
target_compile_options(ggml-webgpu PRIVATE "--use-port=emdawnwebgpu")
target_link_options(ggml-webgpu INTERFACE "--use-port=emdawnwebgpu")
else()
# custom port
target_compile_options(ggml-webgpu PRIVATE "--use-port=${EMDAWNWEBGPU_DIR}/emdawnwebgpu.port.py")
target_link_options(ggml-webgpu INTERFACE "--use-port=${EMDAWNWEBGPU_DIR}/emdawnwebgpu.port.py")
endif()
if (GGML_WEBGPU_JSPI)
target_compile_options(ggml-webgpu PRIVATE "-fwasm-exceptions")
target_link_options(ggml-webgpu INTERFACE "-sJSPI" "-fwasm-exceptions")
else()
target_compile_options(ggml-webgpu PRIVATE "-fexceptions")
target_link_options(ggml-webgpu INTERFACE "-sASYNCIFY" "-exceptions")
endif()
else()
find_package(Dawn REQUIRED)
set(DawnWebGPU_TARGET dawn::webgpu_dawn)
@@ -48,6 +63,9 @@ endif()
if (GGML_WEBGPU_DEBUG)
target_compile_definitions(ggml-webgpu PRIVATE GGML_WEBGPU_DEBUG=1)
if(EMSCRIPTEN)
target_link_options(ggml-webgpu INTERFACE "-sASSERTIONS=2")
endif()
endif()
if (GGML_WEBGPU_CPU_PROFILE)