mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-27 04:23:06 +01:00
adc5dd92e8
* q6_k scale caching * 16 bit unpack * q4_k test (slow) * revert it * q3_k * q2_k * little stuff * try precalculating products of a and q2_k scales * Revert "try precalculating products of a and q2_k scales" This reverts commit 65110b81f23f66331a50c6e889a7c1ab9470a86b. * unpack should be u16, add vim swap to gitignore (about time) * better q4_k scales * q5_k * better q6_k with separate paths for all threads and partial threads in use, plus some more optimizations * q2_k better dequant * q3_k optimizations * q3_k use hmask simd from cpu avx version * make the caches happy * q3_k separate out calculation * q2_k separate out * little stuff * use calc_superblock everywhere * q2_k optimize scale calculation * more barriers
146 lines
1.6 KiB
Plaintext
146 lines
1.6 KiB
Plaintext
# Extensions
|
|
|
|
*.a
|
|
*.bat
|
|
*.bin
|
|
*.d
|
|
*.dll
|
|
*.dot
|
|
*.etag
|
|
*.exe
|
|
*.gcda
|
|
*.gcno
|
|
*.gcov
|
|
*.gguf
|
|
*.gguf.json
|
|
*.lastModified
|
|
*.log
|
|
*.metallib
|
|
*.o
|
|
*.so
|
|
*.swp
|
|
*.tmp
|
|
|
|
# IDE / OS
|
|
|
|
.cache/
|
|
.ccls-cache/
|
|
.direnv/
|
|
.DS_Store
|
|
.envrc
|
|
.idea/
|
|
.swiftpm
|
|
.vs/
|
|
.vscode/
|
|
nppBackup
|
|
|
|
|
|
# Coverage
|
|
|
|
gcovr-report/
|
|
lcov-report/
|
|
|
|
# Build Artifacts
|
|
|
|
tags
|
|
.build/
|
|
build*
|
|
!build-info.cmake
|
|
!build-info.cpp.in
|
|
!build-info.sh
|
|
!build.zig
|
|
!docs/build.md
|
|
/libllama.so
|
|
/llama-*
|
|
/vulkan-shaders-gen
|
|
android-ndk-*
|
|
arm_neon.h
|
|
cmake-build-*
|
|
CMakeSettings.json
|
|
compile_commands.json
|
|
ggml-metal-embed.metal
|
|
llama-batched-swift
|
|
/rpc-server
|
|
out/
|
|
tmp/
|
|
autogen-*.md
|
|
|
|
# Deprecated
|
|
|
|
/main
|
|
/server
|
|
|
|
# CI
|
|
|
|
!.github/workflows/*.yml
|
|
|
|
# Models
|
|
|
|
models/*
|
|
models-mnt
|
|
!models/.editorconfig
|
|
!models/ggml-vocab-*.gguf*
|
|
|
|
# Zig
|
|
zig-out/
|
|
zig-cache/
|
|
|
|
# Logs
|
|
|
|
ppl-*.txt
|
|
qnt-*.txt
|
|
perf-*.txt
|
|
|
|
# Examples
|
|
|
|
examples/jeopardy/results.txt
|
|
examples/server/*.css.hpp
|
|
examples/server/*.html.hpp
|
|
examples/server/*.js.hpp
|
|
examples/server/*.mjs.hpp
|
|
!build_64.sh
|
|
!examples/*.bat
|
|
!examples/*/*.kts
|
|
!examples/*/*/*.kts
|
|
!examples/sycl/*.bat
|
|
!examples/sycl/*.sh
|
|
|
|
# Server Web UI temporary files
|
|
node_modules
|
|
examples/server/webui/dist
|
|
|
|
# Python
|
|
|
|
/.venv
|
|
__pycache__/
|
|
*/poetry.lock
|
|
poetry.toml
|
|
|
|
# Nix
|
|
/result
|
|
|
|
# Test binaries
|
|
/tests/test-backend-ops
|
|
/tests/test-double-float
|
|
/tests/test-grad0
|
|
/tests/test-grammar-parser
|
|
/tests/test-llama-grammar
|
|
/tests/test-opt
|
|
/tests/test-quantize-fns
|
|
/tests/test-quantize-perf
|
|
/tests/test-rope
|
|
/tests/test-sampling
|
|
/tests/test-tokenizer-0
|
|
/tests/test-tokenizer-1-bpe
|
|
/tests/test-tokenizer-1-spm
|
|
|
|
# Scripts
|
|
!/scripts/install-oneapi.bat
|
|
|
|
# Test models for lora adapters
|
|
/lora-tests
|
|
|
|
# Local scripts
|
|
/run-vim.sh
|
|
/run-chat.sh
|