]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
llama : refactor `src/llama.cpp` (#10902)
authorGeorgi Gerganov <redacted>
Fri, 3 Jan 2025 08:18:53 +0000 (10:18 +0200)
committerGitHub <redacted>
Fri, 3 Jan 2025 08:18:53 +0000 (10:18 +0200)
commitf66f5829276650cd83a087ab2cfed1a760183ea1
tree6aa61a1faa0d8e2efd1225b808789d901fb63b14
parent2f0ee84b9b02d2a98742308026f060ebdc2423f1
llama : refactor `src/llama.cpp` (#10902)

* llama : scatter llama.cpp into multiple modules (wip)

* llama : control-vector -> adapter

* llama : arch

* llama : mmap

ggml-ci

* ci : remove BUILD_SHARED_LIBS=OFF

ggml-ci

* llama : arch (cont)

ggml-ci

* llama : chat

ggml-ci

* llama : model

ggml-ci

* llama : hparams

ggml-ci

* llama : adapter

ggml-ci

* examples : fix

ggml-ci

* rebase

ggml-ci

* minor

* llama : kv cache

ggml-ci

* llama : impl

ggml-ci

* llama : batch

ggml-ci

* cont

ggml-ci

* llama : context

ggml-ci

* minor

* llama : context (cont)

ggml-ci

* llama : model loader

ggml-ci

* common : update lora

ggml-ci

* llama : quant

ggml-ci

* llama : quant (cont)

ggml-ci

* minor [no ci]
61 files changed:
.github/workflows/build.yml
common/arg.cpp
common/common.cpp
common/common.h
examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
examples/cvector-generator/cvector-generator.cpp
examples/embedding/embedding.cpp
examples/eval-callback/eval-callback.cpp
examples/gguf-split/gguf-split.cpp
examples/imatrix/imatrix.cpp
examples/infill/infill.cpp
examples/lookahead/lookahead.cpp
examples/lookup/lookup-create.cpp
examples/lookup/lookup-stats.cpp
examples/lookup/lookup.cpp
examples/main/main.cpp
examples/parallel/parallel.cpp
examples/perplexity/perplexity.cpp
examples/quantize-stats/quantize-stats.cpp
examples/retrieval/retrieval.cpp
examples/save-load-state/save-load-state.cpp
examples/server/server.cpp
examples/server/utils.hpp
examples/speculative-simple/speculative-simple.cpp
examples/speculative/speculative.cpp
examples/tts/tts.cpp
include/llama-cpp.h
include/llama.h
src/CMakeLists.txt
src/llama-adapter.cpp [new file with mode: 0644]
src/llama-adapter.h [new file with mode: 0644]
src/llama-arch.cpp [new file with mode: 0644]
src/llama-arch.h [new file with mode: 0644]
src/llama-batch.cpp [new file with mode: 0644]
src/llama-batch.h [new file with mode: 0644]
src/llama-chat.cpp [new file with mode: 0644]
src/llama-chat.h [new file with mode: 0644]
src/llama-context.cpp [new file with mode: 0644]
src/llama-context.h [new file with mode: 0644]
src/llama-cparams.cpp [new file with mode: 0644]
src/llama-cparams.h [new file with mode: 0644]
src/llama-grammar.cpp
src/llama-grammar.h
src/llama-hparams.cpp [new file with mode: 0644]
src/llama-hparams.h [new file with mode: 0644]
src/llama-impl.cpp [new file with mode: 0644]
src/llama-impl.h
src/llama-kv-cache.cpp [new file with mode: 0644]
src/llama-kv-cache.h [new file with mode: 0644]
src/llama-mmap.cpp [new file with mode: 0644]
src/llama-mmap.h [new file with mode: 0644]
src/llama-model-loader.cpp [new file with mode: 0644]
src/llama-model-loader.h [new file with mode: 0644]
src/llama-model.cpp [new file with mode: 0644]
src/llama-model.h [new file with mode: 0644]
src/llama-quant.cpp [new file with mode: 0644]
src/llama-quant.h [new file with mode: 0644]
src/llama-sampling.cpp
src/llama-vocab.cpp
src/llama-vocab.h
src/llama.cpp