squall/ollama
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
b9495ea162
ollama/llm/llama.cpp/generate_windows.go

25 lines
1.6 KiB
Go
Raw Normal View History

subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm
2023-08-31 04:35:03 +08:00
package llm
//go:generate git submodule init
first pass at linux gpu support (#454) * linux gpu support * handle multiple gpus * add cuda docker image (#488) --------- Co-authored-by: Michael Yang <mxyng@pm.me>
2023-09-12 23:04:35 +08:00
//go:generate git submodule update --force ggml
embed libraries using cmake
2023-09-21 03:15:23 +08:00
//go:generate git -C ggml apply ../patches/0001-add-detokenize-endpoint.patch
//go:generate git -C ggml apply ../patches/0002-34B-model-support.patch
first pass at linux gpu support (#454) * linux gpu support * handle multiple gpus * add cuda docker image (#488) --------- Co-authored-by: Michael Yang <mxyng@pm.me>
2023-09-12 23:04:35 +08:00
//go:generate cmake -S ggml -B ggml/build/cpu -DLLAMA_K_QUANTS=on
subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm
2023-08-31 04:35:03 +08:00
//go:generate cmake --build ggml/build/cpu --target server --config Release
rename server subprocess (#700) - this makes it easier to see that the subprocess is associated with ollama
2023-10-06 22:15:42 +08:00
//go:generate cmd /c move ggml\build\cpu\bin\Release\server.exe ggml\build\cpu\bin\Release\ollama-runner.exe
first pass at linux gpu support (#454) * linux gpu support * handle multiple gpus * add cuda docker image (#488) --------- Co-authored-by: Michael Yang <mxyng@pm.me>
2023-09-12 23:04:35 +08:00
//go:generate git submodule update --force gguf
update default log target
2023-10-24 01:41:18 +08:00
//go:generate git -C gguf apply ../patches/0001-update-default-log-target.patch
restore building runner with `AVX` on by default (#900)
2023-10-28 03:13:44 +08:00
//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_K_QUANTS=on -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off
GGUF support (#441)
2023-09-08 01:55:37 +08:00
//go:generate cmake --build gguf/build/cpu --target server --config Release
rename server subprocess (#700) - this makes it easier to see that the subprocess is associated with ollama
2023-10-06 22:15:42 +08:00
//go:generate cmd /c move gguf\build\cpu\bin\Release\server.exe gguf\build\cpu\bin\Release\ollama-runner.exe
windows CUDA support (#1262) * Support cuda build in Windows * Enable dynamic NumGPU allocation for Windows
2023-11-25 06:16:36 +08:00
//go:generate cmake -S ggml -B ggml/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on
//go:generate cmake --build ggml/build/cuda --target server --config Release
//go:generate cmd /c move ggml\build\cuda\bin\Release\server.exe ggml\build\cuda\bin\Release\ollama-runner.exe
//go:generate cmake -S gguf -B gguf/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off
//go:generate cmake --build gguf/build/cuda --target server --config Release
//go:generate cmd /c move gguf\build\cuda\bin\Release\server.exe gguf\build\cuda\bin\Release\ollama-runner.exe
Reference in New Issue Copy Permalink