sync : ggml (new ops, tests, backend, etc.) (#4359)
* sync : ggml (part 1) * sync : ggml (part 2, CUDA) * sync : ggml (part 3, Metal) * ggml : build fixes ggml-ci * cuda : restore lost changes * cuda : restore lost changes (StableLM rope) * cmake : enable separable compilation for CUDA ggml-ci * ggml-cuda : remove device side dequantize * Revert "cmake : enable separable compilation for CUDA" This reverts commit 09e35d04b1c4ca67f9685690160b35bc885a89ac. * cuda : remove assert for rope * tests : add test-backend-ops * ggml : fix bug in ggml_concat * ggml : restore `ggml_get_n_tasks()` logic in `ggml_graph_plan()` * ci : try to fix macOS * ggml-backend : remove backend self-registration * ci : disable Metal for macOS cmake build ggml-ci * metal : fix "supports family" call * metal : fix assert * metal : print resource path ggml-ci --------- Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
parent
bcc0eb4591
commit
fe680e3d10
20 changed files with 4637 additions and 1031 deletions
15
.github/workflows/build.yml
vendored
15
.github/workflows/build.yml
vendored
|
@ -143,6 +143,9 @@ jobs:
|
|||
cd build
|
||||
ctest --verbose
|
||||
|
||||
# TODO: build with LLAMA_NO_METAL because test-backend-ops fail on "Apple Paravirtual device" and I don't know
|
||||
# how to debug it.
|
||||
# ref: https://github.com/ggerganov/llama.cpp/actions/runs/7131777249/job/19420981052#step:5:1124
|
||||
macOS-latest-make:
|
||||
runs-on: macos-latest
|
||||
|
||||
|
@ -160,14 +163,18 @@ jobs:
|
|||
- name: Build
|
||||
id: make_build
|
||||
run: |
|
||||
make -j $(sysctl -n hw.logicalcpu)
|
||||
LLAMA_NO_METAL=1 make -j $(sysctl -n hw.logicalcpu)
|
||||
|
||||
- name: Test
|
||||
id: make_test
|
||||
run: |
|
||||
make tests -j $(sysctl -n hw.logicalcpu)
|
||||
make test -j $(sysctl -n hw.logicalcpu)
|
||||
LLAMA_NO_METAL=1 make tests -j $(sysctl -n hw.logicalcpu)
|
||||
LLAMA_NO_METAL=1 make test -j $(sysctl -n hw.logicalcpu)
|
||||
|
||||
# TODO: build with LLAMA_METAL=OFF because test-backend-ops fail on "Apple Paravirtual device" and I don't know
|
||||
# how to debug it.
|
||||
# ref: https://github.com/ggerganov/llama.cpp/actions/runs/7132125951/job/19422043567?pr=4359#step:5:6584
|
||||
# would be great if we fix these
|
||||
macOS-latest-cmake:
|
||||
runs-on: macos-latest
|
||||
|
||||
|
@ -188,7 +195,7 @@ jobs:
|
|||
sysctl -a
|
||||
mkdir build
|
||||
cd build
|
||||
cmake ..
|
||||
cmake -DLLAMA_METAL=OFF ..
|
||||
cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
|
||||
|
||||
- name: Test
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue