CHANGELOG.md

@@ -7,14 +7,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
-## [0.2.33]
-
-- feat: Update llama.cpp to ggerganov/llama.cpp@faa3526a1eba458120987ed8269e5616385a76f4
-- feat(server): include llama-cpp-python version in openapi spec by @abetlen in cde7514c3d28e6d52f272614e9957208c344dde5
-- fix: use both eos and bos tokens as stop sequences for hf-tokenizer-config chat format. by @abetlen in 5b982d0f8c6f35242c8862ffdce00e17cea0b44f
-- fix: GGUF metadata KV overrides, re #1011 by @phiharri in #1116
-- fix: llama_log_set should be able to accept null pointer by @abetlen in c970d41a85381fd55235136f123422df0bf0c7e7
-
 ## [0.2.32]
 
 - feat: Update llama.cpp to ggerganov/llama.cpp@504dc37be8446fb09b1ede70300250ad41be32a2

README.md

@@ -104,7 +104,6 @@ CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
 ### Windows Notes
 
 If you run into issues where it complains it can't find `'nmake'` `'?'` or CMAKE_C_COMPILER, you can extract w64devkit as [mentioned in llama.cpp repo](https://github.com/ggerganov/llama.cpp#openblas) and add those manually to CMAKE_ARGS before running `pip` install:
-
 ```ps
 $env:CMAKE_GENERATOR = "MinGW Makefiles"
 $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on -DCMAKE_C_COMPILER=C:/w64devkit/bin/gcc.exe -DCMAKE_CXX_COMPILER=C:/w64devkit/bin/g++.exe" 
@@ -119,19 +118,17 @@ Detailed MacOS Metal GPU install documentation is available at [docs/install/mac
 #### M1 Mac Performance Issue
 
 Note: If you are using Apple Silicon (M1) Mac, make sure you have installed a version of Python that supports arm64 architecture. For example:
-
-```bash
+```
 wget https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-MacOSX-arm64.sh
 bash Miniforge3-MacOSX-arm64.sh
 ```
-
 Otherwise, while installing it will build the llama.cpp x86 version which will be 10x slower on Apple Silicon (M1) Mac.
 
 #### M Series Mac Error: `(mach-o file, but is an incompatible architecture (have 'x86_64', need 'arm64'))`
 
 Try installing with
 
-```bash
+```
 CMAKE_ARGS="-DCMAKE_OSX_ARCHITECTURES=arm64 -DCMAKE_APPLE_SILICON_PROCESSOR=arm64 -DLLAMA_METAL=on" pip install --upgrade --verbose --force-reinstall --no-cache-dir llama-cpp-python
 ```
 
@@ -155,15 +152,10 @@ Below is a short example demonstrating how to use the high-level API to for basi
 
 ```python
 >>> from llama_cpp import Llama
->>> llm = Llama(
-      model_path="./models/7B/llama-model.gguf",
-      # n_gpu_layers=-1, # Uncomment to use GPU acceleration 
-      # seed=1337, # Uncomment to set a specific seed
-      # n_ctx=2048, # Uncomment to increase the context window
-)
+>>> llm = Llama(model_path="./models/7B/llama-model.gguf")
 >>> output = llm(
       "Q: Name the planets in the solar system? A: ", # Prompt
-      max_tokens=32, # Generate up to 32 tokens, set to None to generate up to the end of the context window
+      max_tokens=32, # Generate up to 32 tokens
       stop=["Q:", "\n"], # Stop generating just before the model would generate a new question
       echo=True # Echo the prompt back in the output
 ) # Generate a completion, can also call create_completion
@@ -199,10 +191,7 @@ Note that `chat_format` option must be set for the particular model you are usin
 
 ```python
 >>> from llama_cpp import Llama
->>> llm = Llama(
-      model_path="path/to/llama-2/llama-model.gguf",
-      chat_format="llama-2"
-)
+>>> llm = Llama(model_path="path/to/llama-2/llama-model.gguf", chat_format="llama-2")
 >>> llm.create_chat_completion(
       messages = [
           {"role": "system", "content": "You are an assistant who perfectly describes images."},
@@ -425,9 +414,6 @@ pip install -e .[all]
 make clean
 ```
 
-You can also test out specific commits of `lama.cpp` by checking out the desired commit in the `vendor/llama.cpp` submodule and then running `make clean` and `pip install -e .` again. Any changes in the `llama.h` API will require
-changes to the `llama_cpp/llama_cpp.py` file to match the new API (additional changes may be required elsewhere).
-
 ## FAQ
 
 ### Are there pre-built binaries / binary wheels available?

llama_cpp/__init__.py

@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.2.33"
+__version__ = "0.2.32"

llama_cpp/llama_cpp.py

@@ -2528,7 +2528,7 @@ _lib.llama_print_system_info.restype = c_char_p
 # // If this is not called, or NULL is supplied, everything is output on stderr.
 # LLAMA_API void llama_log_set(ggml_log_callback log_callback, void * user_data);
 def llama_log_set(
-    log_callback: Union["ctypes._FuncPointer", c_void_p], user_data: c_void_p  # type: ignore
+    log_callback: "ctypes._FuncPointer", user_data: c_void_p  # type: ignore
 ):
     """Set callback for all future logging events.
 
@@ -2536,7 +2536,7 @@ def llama_log_set(
     return _lib.llama_log_set(log_callback, user_data)
 
 
-_lib.llama_log_set.argtypes = [ctypes.c_void_p, c_void_p]
+_lib.llama_log_set.argtypes = [llama_log_callback, c_void_p]
 _lib.llama_log_set.restype = None
 
 

llama_cpp/server/app.py

@@ -118,7 +118,7 @@ def create_app(
     app = FastAPI(
         middleware=middleware,
         title="🦙 llama.cpp Python API",
-        version=llama_cpp.__version__,
+        version="0.0.1",
     )
     app.add_middleware(
         CORSMiddleware,

vendor/llama.cpp

@@ -1 +1 @@
-Subproject commit faa3526a1eba458120987ed8269e5616385a76f4
+Subproject commit 26d607608d794efa56df3bdb6043a2f94c1d632c