From b2de7f18dfbb93463eeb5b4392117bbe82d5bd1b Mon Sep 17 00:00:00 2001
From: anzz1 <anzz1@live.com>
Date: Sat, 18 Mar 2023 09:27:12 +0200
Subject: [PATCH 1/3] CI Improvements (#230)

* CI Improvements

Manual build feature, autoreleases for Windows

* better CI naming convention

use branch name in releases and tags
---
 .github/workflows/build.yml | 57 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index a94a38991..9c1de5823 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -1,5 +1,20 @@
 name: CI
-on: [push, pull_request]
+
+on:
+  workflow_dispatch: # allows manual triggering
+    inputs:
+      create_release:
+        description: 'Create new release'
+        required: true
+        type: boolean
+  push:
+    paths: ['.github/workflows/**', 'CMakeLists.txt', 'Makefile', '**.h', '*.c', '**.cpp']
+  pull_request:
+    types: [opened, synchronize, edited, reopened, review_requested, ready_for_review]
+    paths: ['CMakeLists.txt', 'Makefile', '**.h', '*.c', '**.cpp']
+
+env:
+ BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
 
 jobs:
   ubuntu-latest-make:
@@ -7,14 +22,17 @@ jobs:
 
     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
 
@@ -42,13 +60,16 @@ jobs:
 
     steps:
       - name: Clone
+        id: checkout
         uses: actions/checkout@v1
 
       - name: Dependencies
+        id: depends
         run: |
           brew update
 
       - name: Build
+        id: make_build
         run: |
           make
 
@@ -75,15 +96,49 @@ jobs:
 
     steps:
       - name: Clone
+        id: checkout
         uses: actions/checkout@v1
 
       - name: Build
+        id: cmake_build
         run: |
           mkdir build
           cd build
           cmake ..
           cmake --build . --config Release
 
+      - name: Get commit hash
+        id: commit
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: pr-mpt/actions-commit-hash@v2
+
+      - name: Pack artifacts
+        id: pack_artifacts
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        run: |
+          7z a llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-x64.zip .\build\Release\*
+
+      - name: Create release
+        id: create_release
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: zendesk/action-create-release@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          tag_name: ${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}
+
+      - name: Upload release
+        id: upload_release
+        if: ${{ ( github.event_name == 'push' && github.ref == 'refs/heads/master' ) || github.event.inputs.create_release == 'true' }}
+        uses: actions/upload-release-asset@v1
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          upload_url: ${{ steps.create_release.outputs.upload_url }} 
+          asset_path: .\llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-x64.zip
+          asset_name: llama-${{ env.BRANCH_NAME }}-${{ steps.commit.outputs.short }}-bin-win-x64.zip
+          asset_content_type: application/octet-stream
+
 #  ubuntu-latest-gcc:
 #    runs-on: ubuntu-latest
 #

From a81d0c2a171a4446e6a21a3ec74a0c0768d71184 Mon Sep 17 00:00:00 2001
From: Gary Linscott <glinscott@gmail.com>
Date: Sat, 18 Mar 2023 04:17:19 -0700
Subject: [PATCH 2/3] Fix n^2 loop in tokenization (#254)

This causes long prompts to parse very slowly.
---
 utils.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/utils.cpp b/utils.cpp
index 22ef59377..efa2e3c35 100644
--- a/utils.cpp
+++ b/utils.cpp
@@ -302,7 +302,7 @@ std::vector<gpt_vocab::id> llama_tokenize(const gpt_vocab & vocab, const std::st
     // Forward pass
     for (int i = 0; i < len; i++) {
         int max_len = std::min(len - i, MAX_TOKEN_LEN);
-        for (int sub_len = 1; sub_len <= len - i; sub_len++) {
+        for (int sub_len = 1; sub_len <= max_len; sub_len++) {
             auto sub = text.substr(i, sub_len);
             auto token = vocab.token_to_id.find(sub);
             if (token != vocab.token_to_id.end()) {

From e03e359730c127f888fcf00e93375771bc0a3500 Mon Sep 17 00:00:00 2001
From: Justin Suess <justin.suess@westpoint.edu>
Date: Sat, 18 Mar 2023 07:44:09 -0400
Subject: [PATCH 3/3] fixed warning with std::ignore about unused function
 result (#151)

fixed warning with std::ignore about unused function result
---
 main.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/main.cpp b/main.cpp
index 39c5d7b76..eb78fe5ab 100644
--- a/main.cpp
+++ b/main.cpp
@@ -1011,7 +1011,7 @@ int main(int argc, char ** argv) {
                     if(params.use_color) printf(ANSI_BOLD ANSI_COLOR_GREEN);
                     if (scanf("%255[^\n]%n%*c", buf, &n_read) <= 0) {
                         // presumable empty line, consume the newline
-                        scanf("%*c");
+                        std::ignore = scanf("%*c");
                         n_read=0;
                     }
                     if(params.use_color) printf(ANSI_COLOR_RESET);