 Daniel Hiltgen
|
0b03b9c32f
llm: Align cmake define for cuda no peer copy (#6455)
|
8 月之前 |
|
Daniel Hiltgen
|
a017cf2fea
Split rocm back out of bundle (#6432)
|
8 月之前 |
 Daniel Hiltgen
|
88bb9e3328
Adjust layout to bin+lib/ollama
|
8 月之前 |
|
Daniel Hiltgen
|
d470ebe78b
Add Jetson cuda variants for arm
|
11 月之前 |
|
Daniel Hiltgen
|
c7bcb00319
Wire up ccache and pigz in the docker based build
|
8 月之前 |
|
Daniel Hiltgen
|
74d45f0102
Refactor linux packaging
|
10 月之前 |
 Jeffrey Morgan
|
efbf41ed81
llm: dont link cuda with compat libs (#5621)
|
9 月之前 |
|
Jeffrey Morgan
|
4e262eb2a8
remove `GGML_CUDA_FORCE_MMQ=on` from build (#5588)
|
9 月之前 |
|
Daniel Hiltgen
|
0bacb30007
Workaround broken ROCm p2p copy
|
10 月之前 |
|
Jeffrey Morgan
|
4607c70641
llm: add `-DBUILD_SHARED_LIBS=off` to common cpu cmake flags (#5520)
|
10 月之前 |
|
Jeffrey Morgan
|
2cc854f8cb
llm: fix missing dylibs by restoring old build behavior on Linux and macOS (#5511)
|
10 月之前 |
|
Jeffrey Morgan
|
8f8e736b13
update llama.cpp submodule to `d7fd29f` (#5475)
|
10 月之前 |
|
Daniel Hiltgen
|
b0930626c5
Add back lower level parallel flags
|
10 月之前 |
|
Jeffrey Morgan
|
152fc202f5
llm: update llama.cpp commit to `7c26775` (#4896)
|
10 月之前 |
|
Daniel Hiltgen
|
ab8c929e20
Add ability to skip oneapi generate
|
11 月之前 |
|
Daniel Hiltgen
|
646371f56d
Merge pull request #3278 from zhewang1-intc/rebase_ollama_main
|
11 月之前 |
 Wang,Zhe
|
fd5971be0b
support ollama run on Intel GPUs
|
11 月之前 |
|
Daniel Hiltgen
|
c48c1d7c46
Port cuda/rocm skip build vars to linux
|
11 月之前 |
 Roy Yang
|
5f73c08729
Remove trailing spaces (#3889)
|
1 年之前 |
|
Daniel Hiltgen
|
cc5a71e0e3
Merge pull request #3709 from remy415/custom-gpu-defs
|
1 年之前 |
 Jeremy
|
440b7190ed
Update gen_linux.sh
|
1 年之前 |
|
Jeremy
|
52f5370c48
add support for custom gpu build flags for llama.cpp
|
1 年之前 |
|
Jeremy
|
7c000ec3ed
adds support for OLLAMA_CUSTOM_GPU_DEFS to customize GPU build flags
|
1 年之前 |
|
Jeremy
|
8aec92fa6d
rearranged conditional logic for static build, dockerfile updated
|
1 年之前 |
|
Jeremy
|
70261b9bb6
move static build to its own flag
|
1 年之前 |
 Blake Mizerany
|
1524f323a3
Revert "build.go: introduce a friendlier way to build Ollama (#3548)" (#3564)
|
1 年之前 |
|
Blake Mizerany
|
fccf3eecaa
build.go: introduce a friendlier way to build Ollama (#3548)
|
1 年之前 |
|
Jeffrey Morgan
|
63efa075a0
update generate scripts with new `LLAMA_CUDA` variable, set `HIP_PLATFORM` to avoid compiler errors (#3528)
|
1 年之前 |
|
Daniel Hiltgen
|
58d95cc9bd
Switch back to subprocessing for llama.cpp
|
1 年之前 |
|
Jeremy
|
dfc6721b20
add support for libcudart.so for CUDA devices (adds Jetson support)
|
1 年之前 |
