Skip to content

Commit

Permalink
chore: bump llama.cpp to b2961 (#45)
Browse files Browse the repository at this point in the history 
Co-authored-by: vansangpfiev <[email protected]>
  • Loading branch information
@vansangpfiev @sangjanai
vansangpfiev and sangjanai authored May 22, 2024
1 parent d10c0da commit b22dbe0
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llama.cpp
Submodule llama.cpp updated 84 files
+8 −9 .devops/nix/package.nix
+73 −0 .github/labeler.yml
+98 −69 .github/workflows/build.yml
+17 −0 .github/workflows/labeler.yml
+2 −6 .github/workflows/server.yml
+62 −41 CMakeLists.txt
+45 −0 CMakePresets.json
+8 −15 Makefile
+24 −48 README.md
+16 −0 cmake/arm64-windows-llvm.cmake
+6 −0 cmake/arm64-windows-msvc.cmake
+32 −2 common/common.cpp
+1 −0 common/common.h
+1 −1 common/grammar-parser.cpp
+6 −6 common/json-schema-to-grammar.cpp
+5 −5 common/log.h
+7 −6 common/sampling.cpp
+38 −46 convert-hf-to-gguf-update.py
+96 −57 convert-hf-to-gguf.py
+0 −143 convert-persimmon-to-gguf.py
+1 −1 convert.py
+20 −4 docs/debugging-tests.md
+2 −2 examples/finetune/finetune.cpp
+13 −8 examples/llama.android/app/src/main/cpp/CMakeLists.txt
+2 −0 examples/main/README.md
+2 −2 examples/main/main.cpp
+4 −1 examples/perplexity/README.md
+2 −2 examples/perplexity/perplexity.cpp
+3 −1 examples/quantize/README.md
+1 −1 examples/quantize/quantize.cpp
+3 −3 examples/quantize/tests.sh
+2 −2 examples/rpc/README.md
+78 −14 examples/rpc/rpc-server.cpp
+5 −6 examples/server/README.md
+7 −8 examples/server/bench/bench.py
+9 −4 examples/server/server.cpp
+46 −9 examples/server/tests/features/results.feature
+38 −3 examples/server/tests/features/steps/steps.py
+2 −2 examples/train-text-from-scratch/train-text-from-scratch.cpp
+72 −30 ggml-cuda.cu
+1 −0 ggml-cuda.h
+25 −0 ggml-cuda/common.cuh
+115 −0 ggml-cuda/fattn-common.cuh
+312 −0 ggml-cuda/fattn-tile-f16.cu
+3 −0 ggml-cuda/fattn-tile-f16.cuh
+309 −0 ggml-cuda/fattn-tile-f32.cu
+3 −0 ggml-cuda/fattn-tile-f32.cuh
+56 −160 ggml-cuda/fattn-vec-f16.cu
+32 −141 ggml-cuda/fattn-vec-f32.cu
+70 −131 ggml-cuda/fattn.cu
+281 −966 ggml-cuda/mmq.cu
+48 −24 ggml-cuda/rope.cu
+2 −11 ggml-cuda/softmax.cu
+40 −0 ggml-impl.h
+4 −0 ggml-kompute.cpp
+68 −53 ggml-metal.m
+17 −16 ggml-metal.metal
+0 −216 ggml-mpi.c
+0 −39 ggml-mpi.h
+5 −2 ggml-opencl.cpp
+2,238 −156 ggml-quants.c
+188 −56 ggml-rpc.cpp
+38 −30 ggml-sycl.cpp
+8,719 −5,064 ggml-vulkan-shaders.hpp
+141 −241 ggml-vulkan.cpp
+627 −255 ggml.c
+37 −9 ggml.h
+65 −30 ggml_vk_generate_shaders.py
+11 −25 gguf-py/gguf/constants.py
+3 −0 gguf-py/gguf/gguf_writer.py
+249 −452 llama.cpp
+4 −3 llama.h
+0 −1 requirements.txt
+0 −2 requirements/requirements-convert-persimmon-to-gguf.txt
+0 −5 scripts/LlamaConfig.cmake.in
+176 −90 scripts/debug-test.sh
+116 −46 scripts/gen-unicode-data.py
+26 −8 tests/test-backend-ops.cpp
+6 −1 tests/test-tokenizer-0.sh
+93 −53 tests/test-tokenizer-random.py
+6,969 −2,169 unicode-data.cpp
+15 −12 unicode-data.h
+89 −111 unicode.cpp
+44 −12 unicode.h

0 comments on commit b22dbe0

Please sign in to comment.