mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-04-28 03:30:20 +00:00
7ca5991d2b
* Faster tensors (#8) Add fast matrix and matrix/vector multiplication. * Use map for shader replacements instead of pair of strings * Wasm (#9) * webgpu : fix build on emscripten * more debugging stuff * test-backend-ops: force single thread on wasm * fix single-thread case for init_tensor_uniform * use jspi * add pthread * test: remember to set n_thread for cpu backend * Add buffer label and enable dawn-specific toggles to turn off some checks * Intermediate state * Fast working f16/f32 vec4 * Working float fast mul mat * Clean up naming of mul_mat to match logical model, start work on q mul_mat * Setup for subgroup matrix mat mul * Basic working subgroup matrix * Working subgroup matrix tiling * Handle weirder sg matrix sizes (but still % sg matrix size) * Working start to gemv * working f16 accumulation with shared memory staging * Print out available subgroup matrix configurations * Vectorize dst stores for sg matrix shader * Gemv working scalar * Minor set_rows optimization (#4) * updated optimization, fixed errors * non vectorized version now dispatches one thread per element * Simplify * Change logic for set_rows pipelines --------- Co-authored-by: Neha Abbas <nehaabbas@macbookpro.lan> Co-authored-by: Neha Abbas <nehaabbas@ReeseLevines-MacBook-Pro.local> Co-authored-by: Reese Levine <reeselevine1@gmail.com> * Comment on dawn toggles * Working subgroup matrix code for (semi)generic sizes * Remove some comments * Cleanup code * Update dawn version and move to portable subgroup size * Try to fix new dawn release * Update subgroup size comment * Only check for subgroup matrix configs if they are supported * Add toggles for subgroup matrix/f16 support on nvidia+vulkan * Make row/col naming consistent * Refactor shared memory loading * Move sg matrix stores to correct file * Working q4_0 * Formatting * Work with emscripten builds * Fix test-backend-ops emscripten for f16/quantized types * Use emscripten memory64 to support get_memory * Add build flags and try ci --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co> * Remove extra whitespace * Move wasm single-thread logic out of test-backend-ops for cpu backend * Disable multiple threads for emscripten single-thread builds in ggml_graph_plan * Fix .gitignore * Add memory64 option and remove unneeded macros for setting threads to 1 --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
151 lines
2.1 KiB
Text
151 lines
2.1 KiB
Text
*.o
|
|
*.a
|
|
*.bin
|
|
*.tmp.yaml
|
|
*.Identifier
|
|
|
|
.DS_Store
|
|
.build/
|
|
.cache/
|
|
.ccls-cache/
|
|
.direnv/
|
|
.envrc
|
|
.swiftpm
|
|
.venv
|
|
.clang-tidy
|
|
.vs/
|
|
.vscode/
|
|
|
|
ggml-metal-embed.metal
|
|
ggml/src/ggml-vulkan-shaders.cpp
|
|
ggml/src/ggml-vulkan-shaders.hpp
|
|
vulkan-shaders-gen.exe
|
|
vulkan-shaders-gen
|
|
ggml/src/ggml-vulkan-shaders-noext.cpp
|
|
ggml/src/ggml-vulkan-shaders-noext.hpp
|
|
vulkan-shaders-gen-noext.exe
|
|
vulkan-shaders-gen-noext
|
|
vulkan-spv-tmp/*
|
|
vulkan-spv-noext-tmp/*
|
|
|
|
lcov-report/
|
|
gcovr-report/
|
|
|
|
build*/
|
|
out/
|
|
tmp/
|
|
autogen-*.md
|
|
|
|
models/*
|
|
models-mnt
|
|
|
|
/Pipfile
|
|
/baby-llama
|
|
/beam-search
|
|
/benchmark-matmult
|
|
/convert-llama2c-to-ggml
|
|
/embd-input-test
|
|
/embedding
|
|
/eval-callback
|
|
/gguf
|
|
/gguf-llama-simple
|
|
/gritlm
|
|
/imatrix
|
|
/infill
|
|
/libllama.so
|
|
/llama-bench
|
|
/lookahead
|
|
/lookup
|
|
/main
|
|
/metal
|
|
/passkey
|
|
/perplexity
|
|
/q8dot
|
|
/quantize
|
|
/quantize-stats
|
|
/result
|
|
/save-load-state
|
|
/server
|
|
/simple
|
|
/batched
|
|
/batched-bench
|
|
/export-lora
|
|
/finetune
|
|
/speculative
|
|
/parallel
|
|
/train-text-from-scratch
|
|
/tokenize
|
|
/vdot
|
|
/common/build-info.cpp
|
|
arm_neon.h
|
|
compile_commands.json
|
|
CMakeSettings.json
|
|
|
|
__pycache__
|
|
dist
|
|
|
|
dist/
|
|
*.spec
|
|
|
|
zig-out/
|
|
zig-cache/
|
|
|
|
ppl-*.txt
|
|
qnt-*.txt
|
|
perf-*.txt
|
|
|
|
poetry.lock
|
|
poetry.toml
|
|
|
|
ggml-metal-merged.metal
|
|
|
|
# Test binaries
|
|
/tests/test-llama-grammar
|
|
tests/test-double-float
|
|
tests/test-grad0
|
|
tests/test-opt
|
|
tests/test-quantize-fns
|
|
tests/test-quantize-perf
|
|
tests/test-sampling
|
|
tests/test-tokenizer-0
|
|
tests/test-tokenizer-0-llama
|
|
tests/test-tokenizer-0-falcon
|
|
tests/test-tokenizer-1-llama
|
|
tests/test-tokenizer-1-bpe
|
|
/tests/test-rope
|
|
/tests/test-backend-ops
|
|
|
|
/koboldcpp_default.so
|
|
/koboldcpp_failsafe.so
|
|
/koboldcpp_noavx2.so
|
|
/koboldcpp_clblast.so
|
|
/koboldcpp_clblast_noavx2.so
|
|
/koboldcpp_clblast_failsafe.so
|
|
/koboldcpp_cublas.so
|
|
/koboldcpp_vulkan.so
|
|
/koboldcpp_vulkan_noavx2.so
|
|
/koboldcpp_default.dll
|
|
/koboldcpp_failsafe.dll
|
|
/koboldcpp_noavx2.dll
|
|
/koboldcpp_clblast.dll
|
|
/koboldcpp_clblast_noavx2.dll
|
|
/koboldcpp_vulkan_noavx2.dll
|
|
/koboldcpp_clblast_failsafe.dll
|
|
/koboldcpp_cublas.dll
|
|
/koboldcpp_vulkan.dll
|
|
/cublas64_11.dll
|
|
/cublasLt64_11.dll
|
|
/cublas64_12.dll
|
|
/cublasLt64_12.dll
|
|
/rocblas/
|
|
rocblas.dll
|
|
hipblas.dll
|
|
koboldcpp_hipblas.so
|
|
koboldcpp_hipblas.dll
|
|
.tokenizer_configs
|
|
|
|
bin/
|
|
conda/
|
|
|
|
# Jetbrains idea folder
|
|
.idea/
|