Skip to content

Commit

Permalink
Merge pull request #199 from janhq/193-feat-nitro-maintainance-work-a…
Browse files Browse the repository at this point in the history 
…nd-version-pump

chore: version pump of llama cpp
  • Loading branch information
@tikikun
tikikun authored Nov 27, 2023
2 parents 63369d2 + a4ee86e commit 96de0b1
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion llama.cpp
Submodule llama.cpp updated 91 files
+20 −0 .github/workflows/python-lint.yml
+2 −0 .gitignore
+15 −2 CMakeLists.txt
+21 −2 Makefile
+16 −4 README.md
+90 −1 common/common.cpp
+16 −0 common/common.h
+13 −0 common/train.cpp
+2 −0 common/train.h
+0 −317 convert-baichuan-hf-to-gguf.py
+0 −247 convert-bloom-hf-to-gguf.py
+0 −253 convert-falcon-hf-to-gguf.py
+0 −221 convert-gptneox-hf-to-gguf.py
+900 −0 convert-hf-to-gguf.py
+34 −42 convert-llama-ggml-to-gguf.py
+0 −227 convert-mpt-hf-to-gguf.py
+4 −2 convert-persimmon-to-gguf.py
+0 −272 convert-refact-hf-to-gguf.py
+0 −210 convert-starcoder-hf-to-gguf.py
+54 −30 convert.py
+ − docs/llama-star/idea-arch.key
+ − docs/llama-star/idea-arch.pdf
+1 −1 docs/token_generation_performance_tips.md
+2 −0 examples/CMakeLists.txt
+1 −1 examples/batched.swift/Sources/main.swift
+12 −9 examples/benchmark/benchmark-matmult.cpp
+2 −2 examples/export-lora/export-lora.cpp
+1 −1 examples/finetune/README.md
+0 −2 examples/finetune/convert-finetune-checkpoint-to-gguf.py
+24 −36 examples/finetune/finetune.cpp
+8 −1 examples/infill/infill.cpp
+2 −2 examples/llava/clip.cpp
+5 −6 examples/llava/llava-cli.cpp
+8 −1 examples/llava/llava.cpp
+5 −0 examples/lookahead/CMakeLists.txt
+487 −0 examples/lookahead/lookahead.cpp
+1 −1 examples/main/README.md
+32 −6 examples/main/main.cpp
+5 −5 examples/metal/metal.cpp
+1 −1 examples/parallel/README.md
+10 −1 examples/parallel/parallel.cpp
+3 −5 examples/perplexity/perplexity.cpp
+51 −0 examples/server/README.md
+2,159 −2,076 examples/server/index.html.hpp
+4 −0 examples/server/public/completion.js
+32 −8 examples/server/public/index.html
+411 −40 examples/server/server.cpp
+15 −2 examples/speculative/speculative.cpp
+5 −0 examples/tokenize/CMakeLists.txt
+44 −0 examples/tokenize/tokenize.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
+383 −210 ggml-alloc.c
+68 −16 ggml-alloc.h
+87 −0 ggml-backend-impl.h
+578 −13 ggml-backend.c
+70 −77 ggml-backend.h
+282 −61 ggml-cuda.cu
+13 −7 ggml-impl.h
+1 −1 ggml-metal.h
+112 −30 ggml-metal.m
+107 −1 ggml-metal.metal
+174 −74 ggml-quants.c
+942 −1,693 ggml.c
+69 −45 ggml.h
+10 −0 gguf-py/README.md
+40 −0 gguf-py/examples/writer.py
+5 −1 gguf-py/gguf/__init__.py
+488 −0 gguf-py/gguf/constants.py
+9 −1,116 gguf-py/gguf/gguf.py
+264 −0 gguf-py/gguf/gguf_reader.py
+412 −0 gguf-py/gguf/gguf_writer.py
+257 −0 gguf-py/gguf/tensor_mapping.py
+183 −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
+117 −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
+578 −55 llama.cpp
+78 −4 llama.h
+ − models/ggml-vocab-stablelm-3b-4e1t.gguf
+1 −0 mypy.ini
+9 −3 scripts/sync-ggml.sh
+2 −0 tests/CMakeLists.txt
+4 −3 tests/test-grad0.cpp
+6 −5 tests/test-opt.cpp
+28 −30 tests/test-tokenizer-0-falcon.py
+26 −28 tests/test-tokenizer-0-llama.py

0 comments on commit 96de0b1

Please sign in to comment.