Daniel Hiltgen
|
0b03b9c32f
llm: Align cmake define for cuda no peer copy (#6455)
|
8 months ago |
Daniel Hiltgen
|
f9e31da946
Review comments
|
8 months ago |
Daniel Hiltgen
|
88bb9e3328
Adjust layout to bin+lib/ollama
|
8 months ago |
Daniel Hiltgen
|
927d98a6cd
Add windows cuda v12 + v11 support
|
9 months ago |
Daniel Hiltgen
|
74d45f0102
Refactor linux packaging
|
9 months ago |
Daniel Hiltgen
|
283948c83b
Adjust windows ROCm discovery
|
9 months ago |
Daniel Hiltgen
|
1f50356e8e
Bump ROCm on windows to 6.1.2
|
9 months ago |
Daniel Hiltgen
|
0bacb30007
Workaround broken ROCm p2p copy
|
10 months ago |
jmorganca
|
f1a379aa56
llm: statically link pthread and stdc++ dependencies in windows build
|
10 months ago |
jmorganca
|
9ae146993e
llm: add `GGML_STATIC` flag to windows static lib
|
10 months ago |
Jeffrey Morgan
|
8f8e736b13
update llama.cpp submodule to `d7fd29f` (#5475)
|
10 months ago |
Daniel Hiltgen
|
96624aa412
Merge pull request #5072 from dhiltgen/windows_path
|
10 months ago |
Daniel Hiltgen
|
b0930626c5
Add back lower level parallel flags
|
10 months ago |
Daniel Hiltgen
|
e890be4814
Revert "More parallelism on windows generate"
|
10 months ago |
Daniel Hiltgen
|
b2799f111b
Move libraries out of users path
|
10 months ago |
Jeffrey Morgan
|
152fc202f5
llm: update llama.cpp commit to `7c26775` (#4896)
|
10 months ago |
Daniel Hiltgen
|
0577af98f4
More parallelism on windows generate
|
10 months ago |
Daniel Hiltgen
|
ab8c929e20
Add ability to skip oneapi generate
|
11 months ago |
Wang,Zhe
|
fd5971be0b
support ollama run on Intel GPUs
|
11 months ago |
Hernan Martinez
|
8a65717f55
Do not build AVX runners on ARM64
|
1 year ago |
Hernan Martinez
|
b438d485f1
Use architecture specific folders in the generate script
|
1 year ago |
Daniel Hiltgen
|
e4859c4563
Fine grain control over windows generate steps
|
1 year ago |
Daniel Hiltgen
|
ed5fb088c4
Fix target in gen_windows.ps1
|
1 year ago |
Daniel Hiltgen
|
421c878a2d
Put back non-avx CPU build for windows
|
1 year ago |
Daniel Hiltgen
|
8671fdeda6
Refactor windows generate for more modular usage
|
1 year ago |
Daniel Hiltgen
|
8feb97dc0d
Move cuda/rocm dependency gathering into generate script
|
1 year ago |
Daniel Hiltgen
|
058f6cd2cc
Move nested payloads to installer and zip file on windows
|
1 year ago |
Jeremy
|
9c0db4cc83
Update gen_windows.ps1
|
1 year ago |
Jeremy
|
6f18297b3a
Update gen_windows.ps1
|
1 year ago |
Jeremy
|
15016413de
Update gen_windows.ps1
|
1 year ago |