Skip to content

Commit

Permalink
chore: bump llama.cpp
Browse files Browse the repository at this point in the history
  • Loading branch information
@hans00
hans00 committed May 14, 2024
1 parent 1c642c7 commit 89c85af
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion src/llama.cpp
Submodule llama.cpp updated 84 files
+45 −2 .github/workflows/build.yml
+14 −12 CMakeLists.txt
+0 −95 ci/run.sh
+19 −5 common/common.cpp
+2 −0 common/common.h
+9 −0 common/grammar-parser.cpp
+3 −3 common/sampling.cpp
+1 −1 common/sampling.h
+25 −2 convert-hf-to-gguf-update.py
+177 −142 convert-hf-to-gguf.py
+0 −150 convert-lora-to-ggml.py
+155 −25 convert.py
+88 −0 docs/debugging-tests.md
+3 −0 examples/CMakeLists.txt
+10 −2 examples/embedding/embedding.cpp
+12 −6 examples/llama-bench/README.md
+56 −7 examples/llama-bench/llama-bench.cpp
+1 −24 examples/llama.android/app/build.gradle.kts
+7 −6 examples/llama.android/app/src/main/java/com/example/llama/MainViewModel.kt
+1 −0 examples/llama.android/build.gradle.kts
+1 −0 examples/llama.android/llama/.gitignore
+1 −1 examples/llama.android/llama/CMakeLists.txt
+0 −0 examples/llama.android/llama/consumer-rules.pro
+21 −0 examples/llama.android/llama/proguard-rules.pro
+24 −0 examples/llama.android/llama/src/androidTest/java/android/llama/cpp/ExampleInstrumentedTest.kt
+4 −0 examples/llama.android/llama/src/main/AndroidManifest.xml
+49 −0 examples/llama.android/llama/src/main/cpp/CMakeLists.txt
+14 −14 examples/llama.android/llama/src/main/cpp/llama-android.cpp
+4 −4 examples/llama.android/llama/src/main/java/android/llama/cpp/LLamaAndroid.kt
+17 −0 examples/llama.android/llama/src/test/java/android/llama/cpp/ExampleUnitTest.kt
+1 −0 examples/llama.android/settings.gradle.kts
+26 −6 examples/llava/llava-cli.cpp
+5 −1 examples/main/main.cpp
+59 −1 examples/perplexity/README.md
+2 −0 examples/rpc/CMakeLists.txt
+74 −0 examples/rpc/README.md
+70 −0 examples/rpc/rpc-server.cpp
+1 −1 examples/server/README.md
+12 −16 examples/server/server.cpp
+5 −2 examples/server/tests/features/steps/steps.py
+1 −1 examples/server/utils.hpp
+2 −2 ggml-backend.c
+14 −6 ggml-cuda.cu
+0 −63 ggml-cuda/alibi.cu
+0 −5 ggml-cuda/alibi.cuh
+4 −0 ggml-cuda/common.cuh
+47 −0 ggml-cuda/fattn-common.cuh
+430 −0 ggml-cuda/fattn-vec-f16.cu
+5 −0 ggml-cuda/fattn-vec-f16.cuh
+384 −0 ggml-cuda/fattn-vec-f32.cu
+3 −0 ggml-cuda/fattn-vec-f32.cuh
+48 −434 ggml-cuda/fattn.cu
+21 −34 ggml-cuda/softmax.cu
+26 −0 ggml-cuda/unary.cu
+3 −0 ggml-cuda/unary.cuh
+9 −3 ggml-kompute.cpp
+93 −117 ggml-metal.m
+56 −71 ggml-metal.metal
+6 −0 ggml-quants.c
+1,023 −0 ggml-rpc.cpp
+24 −0 ggml-rpc.h
+20 −143 ggml-sycl.cpp
+4 −2 ggml-vulkan.cpp
+116 −271 ggml.c
+12 −15 ggml.h
+2 −0 gguf-py/gguf/__init__.py
+62 −0 gguf-py/gguf/constants.py
+16 −51 gguf-py/gguf/gguf_writer.py
+236 −0 gguf-py/gguf/lazy.py
+109 −0 gguf-py/gguf/quants.py
+10 −0 gguf-py/gguf/tensor_mapping.py
+451 −265 llama.cpp
+3 −0 llama.h
+2 −0 models/ggml-vocab-llama-bpe.gguf.inp
+1 −0 models/ggml-vocab-llama-bpe.gguf.out
+0 −1 requirements.txt
+0 −2 requirements/requirements-convert-lora-to-ggml.txt
+6 −2 scripts/compare-llama-bench.py
+117 −0 scripts/debug-test.sh
+1 −1 scripts/sync-ggml.last
+1 −1 tests/CMakeLists.txt
+16 −19 tests/test-backend-ops.cpp
+46 −0 tests/test-grammar-integration.cpp
+27 −3 tests/test-tokenizer-1-bpe.cpp

0 comments on commit 89c85af

Please sign in to comment.