next build (#8539)

* add build to .dockerignore * test: only build one arch * add build to .gitignore * fix ccache path * filter amdgpu targets * only filter if autodetecting * Don't clobber gpu list for default runner This ensures the GPU specific environment variables are set properly * explicitly set CXX compiler for HIP * Update build_windows.ps1 This isn't complete, but is close. Dependencies are missing, and it only builds the "default" preset. * build: add ollama subdir * add .git to .dockerignore * docs: update development.md * update build_darwin.sh * remove unused scripts * llm: add cwd and build/lib/ollama to library paths * default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS * add additional cmake output vars for msvc * interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12 * remove unncessary filepath.Dir, cleanup * add hardware-specific directory to path * use absolute server path * build: linux arm * cmake install...

next build (#8539)
* add build to .dockerignore * test: only build one arch * add build to .gitignore * fix ccache path * filter amdgpu targets * only filter if autodetecting * Don't clobber gpu list for default runner This ensures the GPU specific environment variables are set properly * explicitly set CXX compiler for HIP * Update build_windows.ps1 This isn't complete, but is close. Dependencies are missing, and it only builds the "default" preset. * build: add ollama subdir * add .git to .dockerignore * docs: update development.md * update build_darwin.sh * remove unused scripts * llm: add cwd and build/lib/ollama to library paths * default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS * add additional cmake output vars for msvc * interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12 * remove unncessary filepath.Dir, cleanup * add hardware-specific directory to path * use absolute server path * build: linux arm * cmake install...
dcfb7a10 · Michael Yang · GitHub · 2ef3c803 · 2ef3c803 · 2ef3c803
Unverified Commit dcfb7a10 authored Jan 29, 2025 by Michael Yang Committed by GitHub Jan 29, 2025
20 changed files
--- a/llama/ggml-cuda/template-instances/mmq-instance-q6_k.cu
+++ b/llama/ggml-cuda/template-instances/mmq-instance-q6_k.cu
--- a/llama/ggml-cuda/template-instances/mmq-instance-q8_0.cu
+++ b/llama/ggml-cuda/template-instances/mmq-instance-q8_0.cu
--- a/llama/ggml-cuda/tsembd.cuh
+++ b/llama/ggml-cuda/tsembd.cuh
--- a/llama/ggml-cuda/upscale.cuh
+++ b/llama/ggml-cuda/upscale.cuh
--- a/llama/ggml-cuda/vendors/cuda.h
+++ b/llama/ggml-cuda/vendors/cuda.h
--- a/llama/ggml-cuda/wkv6.cuh
+++ b/llama/ggml-cuda/wkv6.cuh
--- a/llama/ggml-threading.cpp
+++ b/llama/ggml-threading.cpp
--- a/llama/ggml-threading.h
+++ b/llama/ggml-threading.h
--- a/llama/json-schema-to-grammar.h
+++ b/llama/json-schema-to-grammar.h
--- a/llama/llama-cparams.cpp
+++ b/llama/llama-cparams.cpp
--- a/llama/llama-quant.h
+++ b/llama/llama-quant.h
--- a/llama/llama.cpp/.rsync-filter
+++ b/llama/llama.cpp/.rsync-filter
--- a/llama/llama.cpp/LICENSE
+++ b/llama/llama.cpp/LICENSE
--- a/llama/base64.hpp
+++ b/llama/base64.hpp
--- a/llama/common.cpp
+++ b/llama/common.cpp
--- a/llama/llama.cpp/common/common.go
+++ b/llama/llama.cpp/common/common.go
--- a/llama/common.h
+++ b/llama/common.h
--- a/llama/json-schema-to-grammar.cpp
+++ b/llama/json-schema-to-grammar.cpp
--- a/llama/llama.cpp/common/json-schema-to-grammar.h
+++ b/llama/llama.cpp/common/json-schema-to-grammar.h
--- a/llama/json.hpp
+++ b/llama/json.hpp