Update CLBlast to 1.6.0 (#1580)

* Update CLBlast to 1.6.0

.github/workflows/build.yml

@@ -151,7 +151,7 @@ jobs:
     env:
       OPENBLAS_VERSION: 0.3.23
       OPENCL_VERSION: 2023.04.17
-      CLBLAST_VERSION: 1.5.3
+      CLBLAST_VERSION: 1.6.0
 
     strategy:
       matrix:
@@ -184,13 +184,13 @@ jobs:
         id: get_clblast
         if: ${{ matrix.build == 'clblast' }}
         run: |
-          curl.exe -o $env:RUNNER_TEMP/clblast.zip -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-Windows-x64.zip"
+          curl.exe -o $env:RUNNER_TEMP/clblast.7z -L "https://github.com/CNugteren/CLBlast/releases/download/${env:CLBLAST_VERSION}/CLBlast-${env:CLBLAST_VERSION}-windows-x64.7z"
           curl.exe -o $env:RUNNER_TEMP/CLBlast.LICENSE.txt -L "https://github.com/CNugteren/CLBlast/raw/${env:CLBLAST_VERSION}/LICENSE"
-          mkdir $env:RUNNER_TEMP/clblast
-          tar.exe -xvf $env:RUNNER_TEMP/clblast.zip -C $env:RUNNER_TEMP/clblast
+          7z x "-o${env:RUNNER_TEMP}" $env:RUNNER_TEMP/clblast.7z
+          rename-item $env:RUNNER_TEMP/clblast_release_dir clblast
           foreach ($f in (gci -Recurse -Path "$env:RUNNER_TEMP/clblast" -Filter '*.cmake')) {
             $txt = Get-Content -Path $f -Raw
-            $txt.Replace('C:/dependencies/opencl/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8
+            $txt.Replace('C:/vcpkg/packages/opencl_x64-windows/', "$($env:RUNNER_TEMP.Replace('\','/'))/opencl/") | Set-Content -Path $f -Encoding UTF8
           }
 
       - name: Download OpenBLAS

README.md

@@ -391,6 +391,25 @@ Note the use of `--color` to distinguish between user input and generated text.
 
 ![image](https://user-images.githubusercontent.com/1991296/224575029-2af3c7dc-5a65-4f64-a6bb-517a532aea38.png)
 
+### Persistent Interaction
+
+The prompt, user inputs, and model generations can be saved and resumed across calls to `./main` by leveraging `--prompt-cache` and `--prompt-cache-all`. The `./examples/chat-persistent.sh` script demonstrates this with support for long-running, resumable chat sessions. To use this example, you must provide a file to cache the initial chat prompt and a directory to save the chat session, and may optionally provide the same variables as `chat-13B.sh`. The same prompt cache can be reused for new chat sessions. Note that both prompt cache and chat directory are tied to the initial prompt (`PROMPT_TEMPLATE`) and the model file.
+
+```bash
+# Start a new chat
+PROMPT_CACHE_FILE=chat.prompt.bin CHAT_SAVE_DIR=./chat/default ./examples/chat-persistent.sh
+
+# Resume that chat
+PROMPT_CACHE_FILE=chat.prompt.bin CHAT_SAVE_DIR=./chat/default ./examples/chat-persistent.sh
+
+# Start a different chat with the same prompt/model
+PROMPT_CACHE_FILE=chat.prompt.bin CHAT_SAVE_DIR=./chat/another ./examples/chat-persistent.sh
+
+# Different prompt cache for different prompt/model
+PROMPT_TEMPLATE=./prompts/chat-with-bob.txt PROMPT_CACHE_FILE=bob.prompt.bin \
+    CHAT_SAVE_DIR=./chat/bob ./examples/chat-persistent.sh
+```
+
 ### Instruction mode with Alpaca
 
 1. First, download the `ggml` Alpaca model into the `./models` folder

examples/chat-persistent.sh

@@ -23,8 +23,8 @@ CUR_PROMPT_CACHE="${CHAT_SAVE_DIR}/current-cache.bin"
 NEXT_PROMPT_FILE="${CHAT_SAVE_DIR}/next-prompt.txt"
 NEXT_PROMPT_CACHE="${CHAT_SAVE_DIR}/next-cache.bin"
 
-SESSION_SIZE_MSG_PATTERN='main: session file matches \d+ / \d+'
-SAMPLE_TIME_MSG_PATTERN='sample time =\s+\d+.\d+ ms /\s+\d+'
+SESSION_SIZE_MSG_PATTERN='main: session file matches [[:digit:]]+ / [[:digit:]]+'
+SAMPLE_TIME_MSG_PATTERN='sample time =[[:space:]]+[[:digit:]]+.[[:digit:]]+ ms /[[:space:]]+[[:digit:]]+'
 SED_DELETE_MESSAGES="/^(${USER_NAME}:|${AI_NAME}:|\\.\\.\\.)/,\$d"
 
 CTX_SIZE=2048

ggml-opencl.cpp

@@ -488,7 +488,7 @@ void ggml_cl_init(void) {
     CL_CHECK((context = clCreateContext(properties, 1, &device, NULL, NULL, &err), err));
 
     CL_CHECK((queue = clCreateCommandQueue(context, device, CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE, &err),
-        (err != CL_INVALID_PROPERTY && err != CL_INVALID_VALUE ? err :
+        (err != CL_INVALID_QUEUE_PROPERTIES && err != CL_INVALID_VALUE ? err :
         (queue = clCreateCommandQueue(context, device, 0, &err), err)
     )));