llama.cpp: update llama.cpp submodule

danbev · Oct 30, 2024 · acb693a · acb693a
1 parent 3029209
commit acb693a
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 1 deletion.
diff --git a/fundamentals/llama.cpp/.gitignore b/fundamentals/llama.cpp/.gitignore
@@ -15,3 +15,4 @@ tokenize
 v6-Finch-1B6-HF/
 batch
 embeddings
+logging
diff --git a/fundamentals/llama.cpp/llama.cpp b/fundamentals/llama.cpp/llama.cpp
-Original file line number
+Diff line change
@@ Expand Up / @@ -15,3 +15,4 @@ tokenize @@
     v6-Finch-1B6-HF/
     batch
     embeddings
+    logging
+67 −13		common/arg.cpp
+4 −14		common/common.cpp
+55 −34		common/common.h
+19 −11		common/sampling.cpp
+3 −0		convert_hf_to_gguf.py
+1 −0		convert_hf_to_gguf_update.py
+3 −3		convert_lora_to_gguf.py
+22 −110		examples/llama-bench/llama-bench.cpp
+33 −10		examples/main/README.md
+18 −8		examples/server/README.md
+11 −4		examples/server/public/index-new.html
+8 −2		examples/server/public/index.html
+0 −0		examples/server/public/style.css
+64 −33		examples/server/server.cpp
+0 −2		examples/server/themes/buttons-top/index.html
+0 −2		examples/server/themes/wild/index.html
+5 −3		examples/server/utils.hpp
+3 −3		flake.lock
+12 −7		ggml/include/ggml-backend.h
+1 −1		ggml/include/ggml-cuda.h
+268 −0		ggml/src/ggml-aarch64.c
+8 −25		ggml/src/ggml-amx.cpp
+4 −15		ggml/src/ggml-backend-impl.h
+121 −114		ggml/src/ggml-backend.cpp
+5 −15		ggml/src/ggml-blas.cpp
+6 −44		ggml/src/ggml-cann.cpp
+69 −78		ggml/src/ggml-cuda.cu
+1 −1		ggml/src/ggml-cuda/cpy.cuh
+0 −15		ggml/src/ggml-kompute.cpp
+67 −52		ggml/src/ggml-metal.m
+380 −196		ggml/src/ggml-metal.metal
+2 −18		ggml/src/ggml-rpc.cpp
+14 −40		ggml/src/ggml-sycl.cpp
+80 −18		ggml/src/ggml-vulkan.cpp
+3 −1		ggml/src/ggml.c
+57 −0		ggml/src/llamafile/sgemm.cpp
+74 −0		ggml/src/vulkan-shaders/pool2d.comp
+4 −0		ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp
+12 −8		include/llama.h
+1 −1		scripts/compare-llama-bench.py
+1 −1		scripts/run-with-preset.py
+7 −0		scripts/sync-ggml-am.sh
+1 −1		scripts/sync-ggml.last
+3 −0		scripts/sync-ggml.sh
+392 −96		src/llama-sampling.cpp
+18 −0		src/llama-sampling.h
+16 −0		src/llama-vocab.cpp
+5 −0		src/llama-vocab.h
+1,635 −1,516		src/llama.cpp
+4 −0		tests/test-chat-template.cpp
+37 −21		tests/test-sampling.cpp