Merge branch 'master' into openelm

.gitignore

@@ -98,13 +98,14 @@ examples/server/*.mjs.hpp
 
 # Python
 
-__pycache__
+/.venv
-.venv
+__pycache__/
-/Pipfile
+*/poetry.lock
-dist
-poetry.lock
 poetry.toml
 
+# Nix
+/result
+
 # Test binaries
 /tests/test-backend-ops
 /tests/test-double-float

CMakeLists.txt

@@ -156,7 +156,7 @@ install(FILES ${CMAKE_CURRENT_BINARY_DIR}/llama-config.cmake
         DESTINATION ${CMAKE_INSTALL_LIBDIR}/cmake/llama)
 
 install(
-    FILES convert-hf-to-gguf.py
+    FILES convert_hf_to_gguf.py
     PERMISSIONS
         OWNER_READ
         OWNER_WRITE

ci/run.sh

@@ -688,7 +688,7 @@ function gg_run_embd_bge_small {
     (time cmake -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
     (time make -j                                            ) 2>&1 | tee -a $OUT/${ci}-make.log
 
-    python3 ../convert-hf-to-gguf.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf
+    python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf
 
     model_f16="${path_models}/ggml-model-f16.gguf"
     model_q8_0="${path_models}/ggml-model-q8_0.gguf"

examples/llava/requirements.txt

@@ -1,3 +1,3 @@
 -r ../../requirements/requirements-convert-legacy-llama.txt
 pillow~=10.2.0
-torch~=2.1.1
+torch~=2.2.1

pyproject.toml

@@ -0,0 +1,44 @@
+[tool.poetry]
+name = "llama-cpp-scripts"
+version = "0.0.0"
+description = "Scripts that ship with llama.cpp"
+authors = ["GGML <ggml@ggml.ai>"]
+readme = "README.md"
+homepage = "https://ggml.ai"
+repository = "https://github.com/ggerganov/llama.cpp"
+keywords = ["ggml", "gguf", "llama.cpp"]
+packages = [{ include = "*.py", from = "." }]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+
+[tool.poetry.dependencies]
+python = ">=3.9"
+numpy = "^1.25.0"
+sentencepiece = ">=0.1.98,<0.2.0"
+transformers = ">=4.35.2,<5.0.0"
+protobuf = ">=4.21.0,<5.0.0"
+gguf = { path = "./gguf-py" }
+torch = { version = "^2.2.0", source = "pytorch" }
+
+[tool.poetry.dev-dependencies]
+pytest = "^5.2"
+
+
+# Force wheel + cpu
+# For discussion and context see https://github.com/python-poetry/poetry#6409
+[[tool.poetry.source]]
+name = "pytorch"
+url = "https://download.pytorch.org/whl/cpu"
+priority = "explicit"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.scripts]
+llama-convert-hf-to-gguf = "convert_hf_to_gguf:main"
+llama-convert-llama-ggml-to-gguf = "convert_llama_ggml_to_gguf:main"
+llama-ggml-vk-generate-shaders = "ggml_vk_generate_shaders:main"

requirements.txt

@@ -6,6 +6,6 @@
 
 -r ./requirements/requirements-convert-legacy-llama.txt
 
--r ./requirements/requirements-convert-hf-to-gguf.txt
+-r ./requirements/requirements-convert_hf_to_gguf.txt
--r ./requirements/requirements-convert-hf-to-gguf-update.txt
+-r ./requirements/requirements-convert_hf_to_gguf_update.txt
--r ./requirements/requirements-convert-llama-ggml-to-gguf.txt
+-r ./requirements/requirements-convert_llama_ggml_to_gguf.txt

scripts/check-requirements.sh

@@ -167,11 +167,11 @@ if (( do_cleanup )); then
 fi
 
 check_convert_script examples/convert-legacy-llama.py
-for py in convert-*.py; do
+for py in convert_*.py; do
     # skip convert-hf-to-gguf-update.py
     # TODO: the check is failing for some reason:
     #       https://github.com/ggerganov/llama.cpp/actions/runs/8875330981/job/24364557177?pr=6920
-    [[ $py == convert-hf-to-gguf-update.py ]] && continue
+    [[ $py == convert_hf_to_gguf_update.py ]] && continue
 
     check_convert_script "$py"
 done