Skip to content

Commit

Permalink
Bump llama.cpp from ac43576 to 40e07a6
Browse files Browse the repository at this point in the history 
Bumps [llama.cpp](https://github.com/ggerganov/llama.cpp) from `ac43576` to `40e07a6`.
- [Release notes](https://github.com/ggerganov/llama.cpp/releases)
- [Commits](ggerganov/llama.cpp@ac43576...40e07a6)

---
updated-dependencies:
- dependency-name: llama.cpp
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
  • Loading branch information
@dependabot
dependabot[bot] authored Sep 29, 2023
1 parent 79f9587 commit 33f7b41
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llama.cpp
Submodule llama.cpp updated 68 files
+30 −30 .github/workflows/build.yml
+5 −0 .gitignore
+26 −25 CMakeLists.txt
+69 −23 Makefile
+3 −3 Package.swift
+6 −1 README.md
+2 −0 common/CMakeLists.txt
+137 −60 common/common.cpp
+19 −7 common/common.h
+37 −37 common/log.h
+1,496 −0 common/train.cpp
+230 −0 common/train.h
+0 −6 convert-falcon-hf-to-gguf.py
+0 −6 convert-starcoder-hf-to-gguf.py
+1 −1 convert.py
+1 −1 docs/BLIS.md
+4 −0 examples/CMakeLists.txt
+79 −147 examples/baby-llama/baby-llama.cpp
+5 −0 examples/batched/CMakeLists.txt
+44 −0 examples/batched/README.md
+255 −0 examples/batched/batched.cpp
+4 −3 examples/beam-search/beam-search.cpp
+10 −10 examples/embd-input/embd-input-lib.cpp
+1 −1 examples/embd-input/embd-input-test.cpp
+11 −10 examples/embedding/embedding.cpp
+5 −0 examples/export-lora/CMakeLists.txt
+26 −0 examples/export-lora/README.md
+474 −0 examples/export-lora/export-lora.cpp
+5 −0 examples/finetune/CMakeLists.txt
+90 −0 examples/finetune/README.md
+489 −0 examples/finetune/convert-finetune-checkpoint-to-gguf.py
+1,940 −0 examples/finetune/finetune.cpp
+115 −50 examples/llama-bench/llama-bench.cpp
+2 −2 examples/main/README.md
+36 −39 examples/main/main.cpp
+8 −0 examples/parallel/CMakeLists.txt
+3 −0 examples/parallel/README.md
+380 −0 examples/parallel/parallel.cpp
+70 −46 examples/perplexity/perplexity.cpp
+9 −8 examples/quantize-stats/quantize-stats.cpp
+1 −0 examples/quantize/quantize.cpp
+12 −18 examples/save-load-state/save-load-state.cpp
+2 −2 examples/server/README.md
+61 −40 examples/server/server.cpp
+21 −0 examples/simple/README.md
+109 −41 examples/simple/simple.cpp
+13 −10 examples/speculative/speculative.cpp
+8 −3 examples/train-text-from-scratch/README.md
+8 −4 examples/train-text-from-scratch/convert-train-checkpoint-to-gguf.py
+539 −1,500 examples/train-text-from-scratch/train-text-from-scratch.cpp
+8 −2 ggml-alloc.c
+1 −0 ggml-alloc.h
+209 −82 ggml-cuda.cu
+1 −0 ggml-cuda.h
+89 −42 ggml-metal.m
+121 −38 ggml-metal.metal
+1,596 −842 ggml.c
+109 −35 ggml.h
+1,010 −569 llama.cpp
+303 −105 llama.h
+4 −4 pocs/vdot/q8dot.cpp
+2 −0 tests/CMakeLists.txt
+134 −51 tests/test-grad0.cpp
+2 −2 tests/test-opt.cpp
+221 −0 tests/test-rope.cpp
+7 −5 tests/test-tokenizer-0-falcon.cpp
+7 −5 tests/test-tokenizer-0-llama.cpp
+8 −6 tests/test-tokenizer-1-llama.cpp

0 comments on commit 33f7b41

Please sign in to comment.