Merge pull request #151 from janhq/update-submodule-2024-07-19-17-06 · janhq/cortex.llamacpp@c6db47b

Commit

Merge pull request #151 from janhq/update-submodule-2024-07-19-17-06

Update llama.cpp submodule to latest release b3423

jan-service-account authored Jul 19, 2024

2 parents f654587 + f1535a2 commit c6db47b

llama.cpp

Submodule llama.cpp updated 29 files

+1 −1		README.md
+112 −76		convert_hf_to_gguf.py
+19 −10		convert_lora_to_gguf.py
+128 −107		examples/convert_legacy_llama.py
+2 −2		examples/server/public/completion.js
+4 −4		examples/server/public/index-new.html
+1 −1		examples/server/public/index.html
+9 −3		ggml/CMakeLists.txt
+15 −13		ggml/include/ggml-backend.h
+1 −0		ggml/src/ggml-alloc.c
+4 −0		ggml/src/ggml-backend.c
+9 −2		ggml/src/ggml-cuda.cu
+0 −4		ggml/src/ggml-metal.m
+2 −2		ggml/src/ggml-metal.metal
+333 −495		ggml/src/ggml-quants.c
+3 −2		ggml/src/ggml.c
+8 −0		gguf-py/README.md
+2 −0		gguf-py/gguf/__init__.py
+54 −14		gguf-py/gguf/constants.py
+140 −18		gguf-py/gguf/gguf_writer.py
+486 −0		gguf-py/gguf/metadata.py
+69 −0		gguf-py/gguf/utility.py
+1 −0		gguf-py/pyproject.toml
+1 −0		gguf-py/tests/__init__.py
+0 −7		gguf-py/tests/test_gguf.py
+158 −0		gguf-py/tests/test_metadata.py
+1 −1		include/llama.h
+10 −6		src/llama.cpp
+27 −0		tests/test-backend-ops.cpp

Please sign in to comment.