updated llama.cpp · utilityai/llama-cpp-rs@95ab6e3 · GitHub

Commit

updated llama.cpp

Browse files

Loading branch information

Marcus Dunn committed Feb 8, 2024

1 parent 4d0c363 commit 95ab6e3

llama-cpp-sys-2/llama.cpp

Submodule llama.cpp updated 24 files

+8 −4		CMakeLists.txt
+119 −50		Makefile
+4 −6		README-sycl.md
+86 −111		README.md
+0 −40		SHA256SUMS
+20 −2		common/common.cpp
+76 −2		convert-hf-to-gguf.py
+9 −5		convert.py
+1 −13		examples/llava/llava-cli.cpp
+21 −1		examples/server/README.md
+242 −206		examples/server/completion.js.hpp
+2 −1		examples/server/public/completion.js
+59 −40		examples/server/server.cpp
+111 −143		ggml-cuda.cu
+2 −0		ggml-impl.h
+39 −94		ggml-quants.c
+68 −59		ggml-quants.h
+115 −81		ggml-sycl.cpp
+1,513 −1,130		ggml-vulkan.cpp
+14 −9		ggml-vulkan.h
+13 −10		ggml.c
+21 −0		gguf-py/gguf/constants.py
+243 −26		llama.cpp
+50 −42		scripts/server-llm.sh

0 comments on commit `95ab6e3`

Please sign in to comment.