Skip to content

Commit

Permalink
Merge pull request #53 from utilityai/update-llama-cpp-2024-01-31
Browse files Browse the repository at this point in the history 
updated llama.cpp
  • Loading branch information
@MarcusDunn
MarcusDunn authored Jan 31, 2024
2 parents 4621868 + 7b043cf commit a99956b
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llama-cpp-sys-2/llama.cpp
Submodule llama.cpp updated 24 files
+6 −7 README.md
+1 −0 common/common.cpp
+11 −4 examples/llama-bench/llama-bench.cpp
+18 −10 examples/main/main.cpp
+2 −0 examples/quantize-stats/quantize-stats.cpp
+2 −1 examples/quantize/quantize.cpp
+85 −45 examples/server/README.md
+1 −0 examples/server/chat.sh
+59 −50 examples/server/server.cpp
+274 −59 ggml-cuda.cu
+3 −0 ggml-metal.h
+71 −6 ggml-metal.m
+274 −0 ggml-metal.metal
+706 −15 ggml-quants.c
+17 −1 ggml-quants.h
+252 −173 ggml-vulkan.cpp
+165 −35 ggml.c
+3 −0 ggml.h
+21 −8 llama.cpp
+1 −0 llama.h
+1 −1 scripts/sync-ggml.last
+5 −2 tests/test-backend-ops.cpp
+10 −3 tests/test-quantize-fns.cpp
+2 −0 tests/test-quantize-perf.cpp

0 comments on commit a99956b

Please sign in to comment.