Merge branch 'origin/master' into hipblas

Author: SlyEcho

.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

CMakeLists.txt

@@ -73,6 +73,7 @@ option(LLAMA_HIPBLAS                "llama: use hipBLAS"
 
 option(LLAMA_BUILD_TESTS            "llama: build tests"    ${LLAMA_STANDALONE})
 option(LLAMA_BUILD_EXAMPLES         "llama: build examples" ${LLAMA_STANDALONE})
+option(LLAMA_BUILD_SERVER           "llama: build server example"                           OFF)
 
 #
 # Build info header
@@ -201,7 +202,7 @@ if (LLAMA_CLBLAST)
     if (CLBlast_FOUND)
         message(STATUS "CLBlast found")
 
-        set(GGML_OPENCL_SOURCES ggml-opencl.c ggml-opencl.h)
+        set(GGML_OPENCL_SOURCES ggml-opencl.cpp ggml-opencl.h)
 
         add_compile_definitions(GGML_USE_CLBLAST)
 

Makefile

@@ -138,15 +138,16 @@ ggml-cuda.o: ggml-cuda.cu ggml-cuda.h
 endif
 ifdef LLAMA_CLBLAST
 	CFLAGS  += -DGGML_USE_CLBLAST
+	CXXFLAGS  += -DGGML_USE_CLBLAST
 	# Mac provides OpenCL as a framework
 	ifeq ($(UNAME_S),Darwin)
 		LDFLAGS += -lclblast -framework OpenCL
 	else
 		LDFLAGS += -lclblast -lOpenCL
 	endif
 	OBJS    += ggml-opencl.o
-ggml-opencl.o: ggml-opencl.c ggml-opencl.h
-	$(CC) $(CFLAGS) -c $< -o $@
+ggml-opencl.o: ggml-opencl.cpp ggml-opencl.h
+	$(CXX) $(CXXFLAGS) -c $< -o $@
 endif
 ifdef LLAMA_HIPBLAS
 	ROCM_PATH  ?= /opt/rocm
@@ -258,6 +259,6 @@ benchmark-matmult: examples/benchmark/benchmark-matmult.cpp build-info.h ggml.o
 vdot: pocs/vdot/vdot.cpp ggml.o $(OBJS)
 	$(CXX) $(CXXFLAGS) $^ -o $@ $(LDFLAGS)
 
-.PHONY: tests
+.PHONY: tests clean
 tests:
 	bash ./tests/run-tests.sh

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/CMakeLists.txt

@@ -37,4 +37,7 @@ else()
     add_subdirectory(save-load-state)
     add_subdirectory(benchmark)
     add_subdirectory(baby-llama)
+    if(LLAMA_BUILD_SERVER)
+        add_subdirectory(server)
+    endif()
 endif()

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

examples/server/CMakeLists.txt

@@ -0,0 +1,8 @@
+set(TARGET server)
+include_directories(${CMAKE_CURRENT_SOURCE_DIR})
+add_executable(${TARGET} server.cpp json.hpp httplib.h)
+target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
+target_compile_features(${TARGET} PRIVATE cxx_std_11)
+if(TARGET BUILD_INFO)
+  add_dependencies(${TARGET} BUILD_INFO)
+endif()