Merge tag 'v0.2.18' into main

tk-master · Nov 14, 2023 · 96a3776 · 96a3776
2 parents ca30d89 + f2901d8
commit 96a3776
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 2 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.2.18]
+
+- Update llama.cpp to ggerganov/llama.cpp@6bb4908a17150b49373b5f977685b2e180a04f6f
+
 ## [0.2.17]
 
 - Update llama.cpp to ggerganov/llama.cpp@df9d1293defe783f42bc83af732d3c670552c541

diff --git a/llama_cpp/__init__.py b/llama_cpp/__init__.py
@@ -1,4 +1,4 @@
 from .llama_cpp import *
 from .llama import *
 
-__version__ = "0.2.17"
+__version__ = "0.2.18"
diff --git a/vendor/llama.cpp b/vendor/llama.cpp
+9 −0		CMakeLists.txt
+5 −0		Makefile
+3 −2		README.md
+1 −0		common/train.cpp
+2 −0		common/train.h
+1 −1		convert-baichuan-hf-to-gguf.py
+19 −11		convert-hf-to-gguf.py
+2 −22		convert-llama-ggml-to-gguf.py
+1 −1		convert-persimmon-to-gguf.py
+12 −9		convert.py
+1 −1		docs/token_generation_performance_tips.md
+12 −9		examples/benchmark/benchmark-matmult.cpp
+2 −2		examples/export-lora/export-lora.cpp
+11 −12		examples/finetune/finetune.cpp
+2 −2		examples/llava/clip.cpp
+1 −1		examples/main/README.md
+5 −5		examples/metal/metal.cpp
+1 −1		examples/parallel/README.md
+2,388 −2,319		examples/server/index.html.hpp
+30 −8		examples/server/public/index.html
+29 −29		examples/server/server.cpp
+1 −1		examples/train-text-from-scratch/convert-train-checkpoint-to-gguf.py
+11 −12		examples/train-text-from-scratch/train-text-from-scratch.cpp
+378 −208		ggml-alloc.c
+68 −16		ggml-alloc.h
+87 −0		ggml-backend-impl.h
+578 −13		ggml-backend.c
+70 −77		ggml-backend.h
+188 −6		ggml-cuda.cu
+13 −7		ggml-impl.h
+1 −1		ggml-metal.h
+106 −25		ggml-metal.m
+107 −1		ggml-metal.metal
+173 −73		ggml-quants.c
+825 −1,481		ggml.c
+63 −45		ggml.h
+10 −0		gguf-py/README.md
+40 −0		gguf-py/examples/writer.py
+5 −1		gguf-py/gguf/__init__.py
+487 −0		gguf-py/gguf/constants.py
+9 −1,140		gguf-py/gguf/gguf.py
+264 −0		gguf-py/gguf/gguf_reader.py
+409 −0		gguf-py/gguf/gguf_writer.py
+257 −0		gguf-py/gguf/tensor_mapping.py
+164 −0		gguf-py/gguf/vocab.py
+8 −2		gguf-py/pyproject.toml
+12 −0		gguf-py/scripts/__init__.py
+112 −0		gguf-py/scripts/gguf-convert-endian.py
+116 −0		gguf-py/scripts/gguf-dump.py
+90 −0		gguf-py/scripts/gguf-set-metadata.py
+2 −2		gguf-py/tests/test_gguf.py
+2 −2		grammars/README.md
+311 −20		llama.cpp
+ −		models/ggml-vocab-stablelm-3b-4e1t.gguf
+9 −3		scripts/sync-ggml.sh
+2 −0		tests/CMakeLists.txt
+4 −3		tests/test-grad0.cpp
+6 −5		tests/test-opt.cpp