Skip to content

New Q4_0 implementation using 2x F16 instead of 1x F32 #1026

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 4 commits into from
Closed

New Q4_0 implementation using 2x F16 instead of 1x F32 #1026

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7da998d
ggml : initial ARM_NEON 2x F16 Q4_0 implementation
ggerganov Apr 17, 2023
0f5ee9e
ci : do not run on drafts
ggerganov Apr 17, 2023
a8592fb
ggml : explicit assignment of deltas
ggerganov Apr 17, 2023
d1b51ce
ggml : minor
ggerganov Apr 17, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions .github/workflows/build.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,8 @@ on:
required: true
type: boolean
push:
branches:
- master
paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp']
pull_request:
types: [opened, synchronize, edited, reopened, review_requested, ready_for_review]
Expand All @@ -18,6 +20,8 @@ env:

jobs:
ubuntu-latest-make:
if: github.event.pull_request.draft == false

runs-on: ubuntu-latest

steps:
Expand All @@ -37,6 +41,8 @@ jobs:
make

ubuntu-latest-cmake:
if: github.event.pull_request.draft == false

runs-on: ubuntu-latest

steps:
Expand Down Expand Up @@ -65,6 +71,8 @@ jobs:
ctest --verbose

ubuntu-latest-cmake-sanitizer:
if: github.event.pull_request.draft == false

runs-on: ubuntu-latest

continue-on-error: true
Expand Down Expand Up @@ -101,6 +109,8 @@ jobs:
ctest --verbose

macOS-latest-make:
if: github.event.pull_request.draft == false

runs-on: macos-latest

steps:
Expand All @@ -119,6 +129,8 @@ jobs:
make

macOS-latest-cmake:
if: github.event.pull_request.draft == false

runs-on: macOS-latest

steps:
Expand Down Expand Up @@ -146,6 +158,8 @@ jobs:
ctest --verbose

windows-latest-cmake:
if: github.event.pull_request.draft == false

runs-on: windows-latest

strategy:
Expand Down
2 changes: 2 additions & 0 deletions .github/workflows/docker.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@ on:
jobs:
push_to_registry:
name: Push Docker image to Docker Hub
if: github.event.pull_request.draft == false

runs-on: ubuntu-latest
env:
COMMIT_SHA: ${{ github.sha }}
Expand Down
9 changes: 7 additions & 2 deletions Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,10 +31,15 @@ endif
#

# keep standard at C11 and C++11
CFLAGS = -I. -O3 -DNDEBUG -std=c11 -fPIC
CXXFLAGS = -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC
CFLAGS = -I. -O3 -std=c11 -fPIC
CXXFLAGS = -I. -I./examples -O3 -std=c++11 -fPIC
LDFLAGS =

ifndef LLAMA_NO_NDEBUG
CFLAGS += -DNDEBUG
CXXFLAGS += -DNDEBUG
endif

# warnings
CFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -Wno-unused-function
CXXFLAGS += -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar
Expand Down
Loading