updated llama.cpp · utilityai/llama-cpp-rs@a6c0703 · GitHub

Commit

updated llama.cpp

Browse files

Loading branch information

Marcus Dunn committed Feb 27, 2024

1 parent 199ca0e commit a6c0703

llama-cpp-sys-2/llama.cpp

Submodule llama.cpp updated 17 files

+17 −61		.github/workflows/server.yml
+1 −0		README.md
+5 −2		examples/quantize/quantize.cpp
+4 −0		examples/server/server.cpp
+361 −5		ggml-cuda.cu
+31 −6		ggml-metal.m
+487 −0		ggml-metal.metal
+767 −8		ggml-quants.c
+14 −0		ggml-quants.h
+165 −81		ggml-sycl.cpp
+31 −0		ggml.c
+2 −0		ggml.h
+55 −20		llama.cpp
+3 −1		llama.h
+1 −1		tests/test-backend-ops.cpp
+3 −1		tests/test-quantize-fns.cpp
+2 −1		unicode.h

0 comments on commit `a6c0703`

Please sign in to comment.