Skip to content

Commit

Permalink
updated llama.cpp
Browse files Browse the repository at this point in the history
  • Loading branch information
Marcus Dunn committed Feb 20, 2024
1 parent 09f5880 commit fa1d96a
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 76 files
+2 −2 .devops/nix/package.nix
+7 −3 .github/workflows/build.yml
+2 −0 .gitignore
+226 −197 CMakeLists.txt
+23 −9 Makefile
+1 −1 README-sycl.md
+2 −2 README.md
+7 −3 ci/run.sh
+58 −29 common/common.cpp
+2 −2 common/common.h
+3 −3 common/sampling.cpp
+8 −7 common/sampling.h
+12 −10 examples/baby-llama/baby-llama.cpp
+3 −2 examples/batched-bench/batched-bench.cpp
+1 −1 examples/batched.swift/Sources/main.swift
+3 −2 examples/batched/batched.cpp
+2 −1 examples/beam-search/beam-search.cpp
+19 −19 examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
+2 −1 examples/embedding/embedding.cpp
+0 −2 examples/export-lora/export-lora.cpp
+2 −1 examples/imatrix/imatrix.cpp
+2 −1 examples/infill/infill.cpp
+15 −1 examples/json-schema-to-grammar.py
+1 −2 examples/llama-bench/llama-bench.cpp
+2 −2 examples/llama.android/app/src/main/cpp/llama-android.cpp
+1 −1 examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
+3 −3 examples/llava/README.md
+2 −2 examples/llava/clip.cpp
+2 −1 examples/llava/llava-cli.cpp
+0 −8 examples/llava/llava-surgery.py
+0 −1 examples/llava/llava.cpp
+2 −1 examples/lookahead/lookahead.cpp
+2 −1 examples/lookup/lookup.cpp
+5 −1 examples/main/README.md
+2 −1 examples/main/main.cpp
+2 −1 examples/parallel/parallel.cpp
+2 −1 examples/passkey/passkey.cpp
+5 −4 examples/perplexity/perplexity.cpp
+5 −3 examples/quantize/quantize.cpp
+77 −0 examples/server/README.md
+4 −0 examples/server/public/index.html
+162 −33 examples/server/server.cpp
+17 −3 examples/server/utils.hpp
+2 −1 examples/simple/simple.cpp
+2 −1 examples/speculative/speculative.cpp
+1 −1 examples/tokenize/tokenize.cpp
+7 −7 examples/train-text-from-scratch/train-text-from-scratch.cpp
+3 −3 flake.lock
+1 −1 flake.nix
+73 −43 ggml-alloc.c
+10 −9 ggml-backend.c
+319 −234 ggml-cuda.cu
+64 −11 ggml-metal.m
+395 −9 ggml-metal.metal
+638 −41 ggml-quants.c
+12 −2 ggml-quants.h
+82 −29 ggml-vulkan.cpp
+209 −65 ggml.c
+22 −5 ggml.h
+225 −57 llama.cpp
+30 −1 llama.h
+37 −0 scripts/compare-commits.sh
+1 −1 scripts/get-flags.mk
+1 −1 scripts/get-wikitext-2.sh
+1 −1 scripts/sync-ggml.last
+1 −0 tests/CMakeLists.txt
+1 −1 tests/test-autorelease.cpp
+37 −39 tests/test-backend-ops.cpp
+64 −0 tests/test-chat-template.cpp
+10 −10 tests/test-grammar-parser.cpp
+2 −2 tests/test-llama-grammar.cpp
+1 −1 tests/test-model-load-cancel.cpp
+1 −1 tests/test-tokenizer-0-falcon.cpp
+1 −1 tests/test-tokenizer-0-llama.cpp
+1 −1 tests/test-tokenizer-1-bpe.cpp
+1 −1 tests/test-tokenizer-1-llama.cpp

0 comments on commit fa1d96a

Please sign in to comment.