Bump llama.cpp from `bc9d3e3` to `ac43576` (#242) · go-skynet/go-llama.cpp@b8a1245

Commit

Bump llama.cpp from bc9d3e3 to ac43576 (#242)

Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

dependabot[bot] authored Sep 27, 2023

1 parent d84f03c commit b8a1245

+3 −1		CMakeLists.txt
+2 −0		Makefile
+2 −0		Package.swift
+6 −1		README.md
+2 −2		common/common.h
+2 −2		examples/gptneox-wip/falcon-main.cpp
+2 −2		examples/gptneox-wip/gptneox-main.cpp
+271 −0		examples/llama-bench/README.md
+1 −1		examples/llama-bench/llama-bench.cpp
+19 −14		examples/make-ggml.py
+18 −0		examples/perplexity/README.md
+41 −0		examples/quantize/README.md
+21 −0		flake.nix
+4 −0		ggml-metal.h
+74 −42		ggml-metal.m
+7 −0		ggml.h
+1 −1		gguf-py/gguf/gguf.py
+21 −20		llama.cpp
+1 −14		llama.h
+18 −33		scripts/build-info.cmake
+1 −1		scripts/verify-checksum-models.py