Skip to content

Commit

Permalink
Merge pull request #429 from utilityai/update-llama-cpp-2024-07-31
Browse files Browse the repository at this point in the history 
Updated llama-cpp (bot)
  • Loading branch information
@MarcusDunn
MarcusDunn authored Jul 31, 2024
2 parents d70303d + d55559a commit 124d083
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 74 files
+3 −10 .devops/nix/package.nix
+2 −1 .github/workflows/build.yml
+1 −0 .gitignore
+49 −12 Makefile
+1 −0 README.md
+5 −0 common/common.cpp
+28 −0 convert_hf_to_gguf.py
+13 −0 docs/build.md
+1 −1 examples/eval-callback/eval-callback.cpp
+2 −2 examples/imatrix/imatrix.cpp
+3 −3 examples/llama-bench/llama-bench.cpp
+1 −1 examples/llava/clip.cpp
+13 −7 examples/save-load-state/save-load-state.cpp
+1 −1 examples/tokenize/tokenize.cpp
+3 −3 flake.lock
+10 −2 ggml/CMakeLists.txt
+3 −0 ggml/include/ggml-cuda.h
+21 −16 ggml/include/ggml.h
+56 −12 ggml/src/CMakeLists.txt
+18 −24 ggml/src/ggml-alloc.c
+110 −104 ggml/src/ggml-backend.c
+1 −2 ggml/src/ggml-blas.cpp
+20 −20 ggml/src/ggml-cann.cpp
+13 −13 ggml/src/ggml-cann/aclnn_ops.cpp
+5 −1 ggml/src/ggml-common.h
+16 −12 ggml/src/ggml-cuda.cu
+1 −1 ggml/src/ggml-cuda/argsort.cu
+1 −1 ggml/src/ggml-cuda/binbcast.cu
+13 −195 ggml/src/ggml-cuda/common.cuh
+2 −2 ggml/src/ggml-cuda/cpy.cu
+1 −1 ggml/src/ggml-cuda/dmmv.cu
+3 −3 ggml/src/ggml-cuda/fattn-common.cuh
+1 −1 ggml/src/ggml-cuda/fattn-tile-f16.cu
+1 −1 ggml/src/ggml-cuda/fattn-tile-f32.cu
+5 −5 ggml/src/ggml-cuda/fattn.cu
+1 −2 ggml/src/ggml-cuda/getrows.cu
+1 −1 ggml/src/ggml-cuda/mmq.cu
+2 −2 ggml/src/ggml-cuda/mmq.cuh
+3 −3 ggml/src/ggml-cuda/mmvq.cu
+1 −1 ggml/src/ggml-cuda/quantize.cu
+2 −2 ggml/src/ggml-cuda/rope.cu
+14 −0 ggml/src/ggml-cuda/vendors/cuda.h
+177 −0 ggml/src/ggml-cuda/vendors/hip.h
+171 −0 ggml/src/ggml-cuda/vendors/musa.h
+108 −8 ggml/src/ggml-impl.h
+4 −4 ggml/src/ggml-kompute.cpp
+21 −21 ggml/src/ggml-metal.m
+34 −22 ggml/src/ggml-quants.c
+24 −8 ggml/src/ggml-sycl.cpp
+2 −0 ggml/src/ggml-sycl/backend.hpp
+1 −1 ggml/src/ggml-sycl/common.hpp
+99 −0 ggml/src/ggml-sycl/conv.cpp
+21 −0 ggml/src/ggml-sycl/conv.hpp
+1 −1 ggml/src/ggml-sycl/dmmv.cpp
+1 −1 ggml/src/ggml-sycl/dpct/helper.hpp
+11 −11 ggml/src/ggml-sycl/mmq.cpp
+1 −1 ggml/src/ggml-sycl/mmvq.cpp
+2 −0 ggml/src/ggml-sycl/presets.hpp
+2 −2 ggml/src/ggml-sycl/rope.cpp
+71 −0 ggml/src/ggml-sycl/tsembd.cpp
+21 −0 ggml/src/ggml-sycl/tsembd.hpp
+31 −31 ggml/src/ggml-vulkan.cpp
+471 −430 ggml/src/ggml.c
+30 −3 ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp
+10 −1 gguf-py/gguf/gguf_writer.py
+13 −10 include/llama.h
+6 −0 scripts/sync-ggml-am.sh
+1 −1 scripts/sync-ggml.last
+3 −0 scripts/sync-ggml.sh
+2 −2 src/llama-grammar.cpp
+7 −7 src/llama-vocab.cpp
+713 −775 src/llama.cpp
+4 −4 tests/test-backend-ops.cpp
+5 −5 tests/test-sampling.cpp

0 comments on commit 124d083

Please sign in to comment.