Merge branch 'main' into cuda

Author: Smartappli

.github/workflows/build-docker.yaml

@@ -31,7 +31,7 @@ jobs:
 
       - name: Build and push
         id: docker_build
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           context: .
           file: "docker/simple/Dockerfile"

CHANGELOG.md

@@ -7,6 +7,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.79]
+
+- feat: Update llama.cpp to ggerganov/llama.cpp@9c77ec1d74874ee22bdef8f110e8e8d41389abf2
+- feat(ci): Update workflows and pre-built wheels by @Smartappli in #1416
+- feat: Add .close() method to Llama class to explicitly free model from memory by @jkawamoto in #1513
+- feat: Support SPM infill by @CISC in #1492
+
 ## [0.2.78]
 
 - feat: Update llama.cpp to ggerganov/llama.cpp@fd5ea0f897ecb3659d6c269ef6f3d833e865ead7

Makefile

@@ -24,9 +24,6 @@ build.debug:
 build.cuda:
 	CMAKE_ARGS="-DLLAMA_CUDA=on" python3 -m pip install --verbose -e .
 
-build.opencl:
-	CMAKE_ARGS="-DLLAMA_CLBLAST=on" python3 -m pip install --verbose -e .
-
 build.openblas:
 	CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" python3 -m pip install --verbose -e .
 

README.md

@@ -166,17 +166,6 @@ pip install llama-cpp-python \
   --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/metal
 ```
 
-</details>
-<details>
-
-<summary>CLBlast (OpenCL)</summary>
-
-To install with CLBlast, set the `LLAMA_CLBLAST=on` environment variable before installing:
-
-```bash
-CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
-```
-
 </details>
 
 <details>
@@ -339,7 +328,7 @@ You'll need to install the `huggingface-hub` package to use this feature (`pip i
 
 ```python
 llm = Llama.from_pretrained(
-    repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
+    repo_id="Qwen/Qwen2-0.5B-Instruct-GGUF",
     filename="*q8_0.gguf",
     verbose=False
 )
@@ -700,7 +689,7 @@ For possible options, see [llama_cpp/llama_chat_format.py](llama_cpp/llama_chat_
 If you have `huggingface-hub` installed, you can also use the `--hf_model_repo_id` flag to load a model from the Hugging Face Hub.
 
 ```bash
-python3 -m llama_cpp.server --hf_model_repo_id Qwen/Qwen1.5-0.5B-Chat-GGUF --model '*q8_0.gguf'
+python3 -m llama_cpp.server --hf_model_repo_id Qwen/Qwen2-0.5B-Instruct-GGUF --model '*q8_0.gguf'
 ```
 
 ### Web Server Features

llama_cpp/__init__.py

@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.2.78"
+__version__ = "0.2.79"

llama_cpp/_internals.py

@@ -64,6 +64,9 @@ def free_model():
     def close(self):
         self._exit_stack.close()
 
+    def __del__(self):
+        self.close()
+
     def vocab_type(self) -> int:
         assert self.model is not None
         return llama_cpp.llama_vocab_type(self.model)
@@ -292,6 +295,9 @@ def free_ctx():
     def close(self):
         self._exit_stack.close()
 
+    def __del__(self):
+        self.close()
+
     def n_ctx(self) -> int:
         assert self.ctx is not None
         return llama_cpp.llama_n_ctx(self.ctx)
@@ -531,6 +537,9 @@ def free_batch():
     def close(self):
         self._exit_stack.close()
 
+    def __del__(self):
+        self.close()
+
     def n_tokens(self) -> int:
         assert self.batch is not None
         return self.batch.n_tokens

llama_cpp/llama.py

@@ -1968,6 +1968,9 @@ def close(self) -> None:
         """Explicitly free the model from memory."""
         self._stack.close()
 
+    def __del__(self) -> None:
+        self.close()
+
     @staticmethod
     def logits_to_logprobs(
         logits: Union[npt.NDArray[np.single], List], axis: int = -1

llama_cpp/llama_cpp.py

@@ -301,6 +301,7 @@ def byref(obj: CtypesCData, offset: Optional[int] = None) -> CtypesRef[CtypesCDa
 #     LLAMA_VOCAB_PRE_TYPE_OLMO           = 12,
 #     LLAMA_VOCAB_PRE_TYPE_DBRX           = 13,
 #     LLAMA_VOCAB_PRE_TYPE_SMAUG          = 14,
+#     LLAMA_VOCAB_PRE_TYPE_PORO           = 15,
 # };
 LLAMA_VOCAB_PRE_TYPE_DEFAULT = 0
 LLAMA_VOCAB_PRE_TYPE_LLAMA3 = 1
@@ -317,6 +318,7 @@ def byref(obj: CtypesCData, offset: Optional[int] = None) -> CtypesRef[CtypesCDa
 LLAMA_VOCAB_PRE_TYPE_OLMO = 12
 LLAMA_VOCAB_PRE_TYPE_DBRX = 13
 LLAMA_VOCAB_PRE_TYPE_SMAUG = 14
+LLAMA_VOCAB_PRE_TYPE_PORO = 15
 
 
 # // note: these values should be synchronized with ggml_rope
@@ -466,11 +468,13 @@ def byref(obj: CtypesCData, offset: Optional[int] = None) -> CtypesRef[CtypesCDa
 #     LLAMA_POOLING_TYPE_NONE = 0,
 #     LLAMA_POOLING_TYPE_MEAN = 1,
 #     LLAMA_POOLING_TYPE_CLS  = 2,
+#     LLAMA_POOLING_TYPE_LAST = 3,
 # };
 LLAMA_POOLING_TYPE_UNSPECIFIED = -1
 LLAMA_POOLING_TYPE_NONE = 0
 LLAMA_POOLING_TYPE_MEAN = 1
 LLAMA_POOLING_TYPE_CLS = 2
+LLAMA_POOLING_TYPE_LAST = 3   
 
 # enum llama_split_mode {
 #     LLAMA_SPLIT_MODE_NONE    = 0, // single GPU
@@ -759,7 +763,6 @@ class llama_model_params(ctypes.Structure):
 
 #     enum llama_rope_scaling_type rope_scaling_type; // RoPE scaling type, from `enum llama_rope_scaling_type`
 #     enum llama_pooling_type      pooling_type;      // whether to pool (sum) embedding results by sequence id
-#                                                     // (ignored if no pooling layer)
 
 #     // ref: https://github.com/ggerganov/llama.cpp/pull/2054
 #     float    rope_freq_base;   // RoPE base frequency, 0 = from model
@@ -2314,6 +2317,16 @@ def llama_n_threads_batch(ctx: llama_context_p, /) -> int:
     ...
 
 
+# // Set whether the model is in embeddings model or not
+# // If true, embeddings will be returned but logits will not
+# LLAMA_API void llama_set_embeddings(struct llama_context * ctx, bool embeddings);
+@ctypes_function("llama_set_embeddings", [llama_context_p_ctypes, ctypes.c_bool], None)
+def llama_set_embeddings(ctx: llama_context_p, embeddings: bool, /):
+    """Set whether the model is in embeddings model or not
+    If true, embeddings will be returned but logits will not"""
+    ...
+
+
 # // Set whether to use causal attention or not
 # // If set to true, the model will only attend to the past tokens
 # LLAMA_API void llama_set_causal_attn(struct llama_context * ctx, bool causal_attn);