Skip to content

Commit

Permalink
Update submodule to latest release b4474
Browse files Browse the repository at this point in the history
  • Loading branch information
github-actions[bot] committed Jan 13, 2025
1 parent fde2c39 commit 848b0e1
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llama.cpp
Submodule llama.cpp updated 85 files
+96 −6 CONTRIBUTING.md
+22 −11 common/arg.cpp
+163 −59 common/common.cpp
+26 −8 common/common.h
+11 −6 common/sampling.cpp
+18 −15 common/speculative.cpp
+19 −1 convert_hf_to_gguf.py
+1 −1 examples/batched-bench/batched-bench.cpp
+3 −3 examples/batched.swift/Sources/main.swift
+6 −4 examples/batched/batched.cpp
+1 −1 examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
+5 −3 examples/cvector-generator/cvector-generator.cpp
+5 −3 examples/embedding/embedding.cpp
+4 −1 examples/eval-callback/eval-callback.cpp
+1 −2 examples/export-lora/export-lora.cpp
+11 −8 examples/gritlm/gritlm.cpp
+9 −7 examples/imatrix/imatrix.cpp
+21 −19 examples/infill/infill.cpp
+7 −5 examples/llama-bench/llama-bench.cpp
+4 −3 examples/llama.android/llama/src/main/cpp/llama-android.cpp
+3 −3 examples/llama.swiftui/llama.cpp.swift/LibLlama.swift
+6 −3 examples/llava/llava-cli.cpp
+2 −2 examples/llava/llava.cpp
+6 −2 examples/llava/minicpmv-cli.cpp
+8 −5 examples/llava/qwen2vl-cli.cpp
+4 −2 examples/lookahead/lookahead.cpp
+3 −1 examples/lookup/lookup.cpp
+12 −11 examples/main/main.cpp
+3 −1 examples/parallel/parallel.cpp
+5 −3 examples/passkey/passkey.cpp
+34 −18 examples/perplexity/perplexity.cpp
+1 −1 examples/quantize-stats/quantize-stats.cpp
+6 −4 examples/retrieval/retrieval.cpp
+14 −12 examples/run/run.cpp
+2 −2 examples/save-load-state/save-load-state.cpp
+ examples/server/public/index.html.gz
+40 −34 examples/server/server.cpp
+44 −39 examples/server/utils.hpp
+3 −2 examples/server/webui/index.html
+12 −8 examples/simple-chat/simple-chat.cpp
+7 −6 examples/simple/simple.cpp
+3 −1 examples/speculative-simple/speculative-simple.cpp
+16 −13 examples/speculative/speculative.cpp
+5 −3 examples/tokenize/tokenize.cpp
+80 −0 examples/tts/README.md
+14 −12 examples/tts/tts.cpp
+214 −190 ggml/src/ggml-cuda/ggml-cuda.cu
+3 −1 ggml/src/ggml-hip/CMakeLists.txt
+2 −0 gguf-py/README.md
+0 −2 gguf-py/gguf/constants.py
+0 −3 gguf-py/gguf/gguf_writer.py
+2 −2 gguf-py/gguf/scripts/gguf_convert_endian.py
+2 −2 gguf-py/gguf/scripts/gguf_dump.py
+2 −2 gguf-py/gguf/scripts/gguf_hash.py
+2 −2 gguf-py/gguf/scripts/gguf_new_metadata.py
+2 −2 gguf-py/gguf/scripts/gguf_set_metadata.py
+1 −1 gguf-py/pyproject.toml
+3 −3 include/llama-cpp.h
+106 −75 include/llama.h
+39 −38 src/llama-adapter.cpp
+30 −29 src/llama-adapter.h
+1 −0 src/llama-arch.cpp
+1 −0 src/llama-arch.h
+9 −5 src/llama-context.cpp
+5 −5 src/llama-context.h
+4 −4 src/llama-grammar.cpp
+0 −2 src/llama-hparams.h
+1 −1 src/llama-kv-cache.cpp
+1 −1 src/llama-mmap.cpp
+61 −0 src/llama-model-loader.cpp
+4 −0 src/llama-model-loader.h
+2,920 −1,185 src/llama-model.cpp
+100 −124 src/llama-model.h
+8 −6 src/llama-quant.cpp
+30 −28 src/llama-sampling.cpp
+3 −19 src/llama-sampling.h
+1,833 −570 src/llama-vocab.cpp
+97 −154 src/llama-vocab.h
+126 −2,806 src/llama.cpp
+1 −1 tests/test-autorelease.cpp
+1 −2 tests/test-chat-template.cpp
+1 −1 tests/test-tokenizer-0.cpp
+6 −4 tests/test-tokenizer-1-bpe.cpp
+5 −3 tests/test-tokenizer-1-spm.cpp
+2 −2 tests/test-tokenizer-random.py

0 comments on commit 848b0e1

Please sign in to comment.