Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main

Author: abetlen

CHANGELOG.md

@@ -7,6 +7,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.73]
+
+- feat: Update llama.cpp to ggerganov/llama.cpp@25c6e82e7a1ad25a42b0894e87d9b5c557409516
+- fix: Clear kv cache at beginning of image chat formats to avoid bug when image is evaluated first by @abetlen in ac55d0a175115d1e719672ce1cb1bec776c738b1
+
 ## [0.2.72]
 
 - fix(security): Remote Code Execution by Server-Side Template Injection in Model Metadata by @retr0reg in b454f40a9a1787b2b5659cd2cb00819d983185df

CMakeLists.txt

@@ -51,8 +51,9 @@ if (LLAMA_BUILD)
     )
 
     if (LLAVA_BUILD)
-        if (LLAMA_CUBLAS)
+        if (LLAMA_CUBLAS OR LLAMA_CUDA)
             add_compile_definitions(GGML_USE_CUBLAS)
+            add_compile_definitions(GGML_USE_CUDA)
         endif()
 
         if (LLAMA_METAL)

Makefile

@@ -16,7 +16,7 @@ build.debug:
 	CMAKE_ARGS="-DCMAKE_BUILD_TYPE=Debug" python3 -m pip install --verbose --config-settings=cmake.verbose=true --config-settings=logging.level=INFO --config-settings=install.strip=false  --editable .
 
 build.cuda:
-	CMAKE_ARGS="-DLLAMA_CUBLAS=on" python3 -m pip install --verbose -e .
+	CMAKE_ARGS="-DLLAMA_CUDA=on" python3 -m pip install --verbose -e .
 
 build.opencl:
 	CMAKE_ARGS="-DLLAMA_CLBLAST=on" python3 -m pip install --verbose -e .

README.md

@@ -550,7 +550,7 @@ llm = Llama.from_pretrained(
   n_ctx=2048, # n_ctx should be increased to accommodate the image embedding
 )
 
-respoonse = llm.create_chat_completion(
+response = llm.create_chat_completion(
     messages = [
         {
             "role": "user",

llama_cpp/__init__.py

@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.2.72"
+__version__ = "0.2.73"

llama_cpp/llama_chat_format.py

@@ -2637,6 +2637,7 @@ def embed_image_bytes(image_bytes: bytes):
 
         # Evaluate prompt
         llama.reset()
+        llama._ctx.kv_cache_clear()
         for type_, value in split_text:
             if type_ == "text":
                 tokens = llama.tokenize(value.encode("utf8"), add_bos=False, special=True)