Merge pull request #28 from saharNooby/ggml-to-submodule

Move ggml to submodule

.github/workflows/build.yml

@@ -9,41 +9,24 @@ on:
         required: true
         type: boolean
   push:
-    paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp']
+    paths: ['.github/workflows/**', '**/CMakeLists.txt', '**/*.h', '**/*.c', '**/*.cpp']
   pull_request:
     types: [opened, synchronize, edited, reopened, review_requested, ready_for_review]
-    paths: ['**/CMakeLists.txt', '**/Makefile', '**/*.h', '**/*.c', '**/*.cpp']
+    paths: ['**/CMakeLists.txt', '**/*.h', '**/*.c', '**/*.cpp']
 
 env:
  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
 
 jobs:
-  ubuntu-latest-make:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v1
-
-      - name: Dependencies
-        id: depends
-        run: |
-          sudo apt-get update
-          sudo apt-get install build-essential
-
-      - name: Build
-        id: make_build
-        run: |
-          make
-
   ubuntu-latest-cmake:
     runs-on: ubuntu-latest
 
     steps:
       - name: Clone
         id: checkout
-        uses: actions/checkout@v1
+        uses: actions/checkout@v3
+        with:
+          submodules: 'recursive'
 
       - name: Dependencies
         id: depends
@@ -85,31 +68,15 @@ jobs:
           path: |
             rwkv-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-${{ steps.system-info.outputs.OS_TYPE }}-${{ steps.system-info.outputs.OS_NAME }}-${{ steps.system-info.outputs.OS_VERSION }}-${{ steps.system-info.outputs.CPU_ARCH }}.zip
 
-  macOS-latest-make:
-    runs-on: macos-latest
-
-    steps:
-      - name: Clone
-        id: checkout
-        uses: actions/checkout@v1
-
-      - name: Dependencies
-        id: depends
-        run: |
-          brew update
-
-      - name: Build
-        id: make_build
-        run: |
-          make
-
   macOS-latest-cmake:
     runs-on: macOS-latest
 
     steps:
       - name: Clone
         id: checkout
-        uses: actions/checkout@v1
+        uses: actions/checkout@v3
+        with:
+          submodules: 'recursive'
 
       - name: Dependencies
         id: depends
@@ -167,7 +134,9 @@ jobs:
     steps:
       - name: Clone
         id: checkout
-        uses: actions/checkout@v1
+        uses: actions/checkout@v3
+        with:
+          submodules: 'recursive'
 
       - name: Build
         id: cmake_build
@@ -222,9 +191,7 @@ jobs:
     runs-on: ubuntu-latest
 
     needs:
-      - ubuntu-latest-make
       - ubuntu-latest-cmake
-      - macOS-latest-make
       - macOS-latest-cmake
       - windows-latest-cmake
 

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "ggml"]
+	path = ggml
+	url = https://github.com/saharNooby/ggml

CMakeLists.txt

@@ -222,13 +222,12 @@ endif()
 # Build libraries
 #
 
-add_library(ggml OBJECT
-            ggml.c
-            ggml.h)
+if (MSVC)
+    add_compile_definitions(_CRT_SECURE_NO_WARNINGS)
+endif()
+
+add_subdirectory(ggml)
 
-target_include_directories(ggml PUBLIC .)
-target_compile_features(ggml PUBLIC c_std_11) # don't bump
-target_link_libraries(ggml PRIVATE Threads::Threads ${RWKV_EXTRA_LIBS})
 if (BUILD_SHARED_LIBS)
     set_target_properties(ggml PROPERTIES POSITION_INDEPENDENT_CODE ON)
 endif()

README.md

@@ -12,7 +12,7 @@ Loading LoRA checkpoints in [Blealtan's format](https://github.com/Blealtan/RWKV
 
 **TODO (contributions welcome!)**:
 
-1. Optimize AVX2 implementation of `Q4_1_O` matmul — currently, it is as slow as `FP32`
+1. Optimize AVX2 implementation of `Q4_1_O` matmul — currently, it is 40% slower than `Q4_1`
 2. Measure latency and perplexity of different model sizes (169M to 14B) and data types (`FP32`, `FP16`, `Q4_0`, `Q4_1`, `Q4_1_O`)
 3. Test on Linux (including Colab) and MacOS
 4. Make required memory calculation more robust (see [#4](https://github.com/saharNooby/rwkv.cpp/issues/4))
@@ -24,7 +24,7 @@ Loading LoRA checkpoints in [Blealtan's format](https://github.com/Blealtan/RWKV
 **Requirements**: [git](https://gitforwindows.org/).
 
 ```commandline
-git clone https://github.com/saharNooby/rwkv.cpp.git
+git clone --recursive https://github.com/saharNooby/rwkv.cpp.git
 cd rwkv.cpp
 ```
 
@@ -91,9 +91,9 @@ python rwkv/quantize.py ~/Downloads/rwkv.cpp-169M.bin ~/Downloads/rwkv.cpp-169M-
 
 Formats available:
 
-- `4`: `Q4_1_O`, best quality, very slow (as `FP32`).
-- `3`: `Q4_1`, poor quality, very fast (as `FP16`).
-- `2`: `Q4_0`, worst quality, breaks larger models, moderately fast (between `FP16` and `FP32`).
+- `4`: `Q4_1_O`, best quality, slow (30% slower than `FP16`).
+- `3`: `Q4_1`, poor quality, fast (comparable to `FP16`).
+- `2`: `Q4_0`, worst quality, breaks larger models, very fast.
 
 ### 4. Run the model