Matt Williams
|
a314b6c2a9
add faq on models downloaded from hf
|
1 anno fa |
Daniel Hiltgen
|
cd8fad3398
Merge pull request #1790 from dhiltgen/llm_code_shuffle
|
1 anno fa |
Daniel Hiltgen
|
9983fa5f4e
Cleaup stale submodule
|
1 anno fa |
Daniel Hiltgen
|
dfda91c2ee
Merge pull request #1788 from dhiltgen/llm_code_shuffle
|
1 anno fa |
Daniel Hiltgen
|
fac9060da5
Init submodule with new path
|
1 anno fa |
Daniel Hiltgen
|
a554616f8e
remove old llama.cpp submodule path
|
1 anno fa |
Daniel Hiltgen
|
77d96da94b
Code shuffle to clean up the llm dir
|
1 anno fa |
Brian Murray
|
0d6e3565ae
Add embeddings to API (#1773)
|
1 anno fa |
Daniel Hiltgen
|
b5939008a1
Merge pull request #1785 from dhiltgen/win_native_cli
|
1 anno fa |
Daniel Hiltgen
|
e9ce91e9a6
Load dynamic cpu lib on windows
|
1 anno fa |
Bruce MacDonald
|
4ad6c9b11f
fix: pull either original model or from model on create (#1774)
|
1 anno fa |
Jeffrey Morgan
|
c0285158a9
tweak memory requirements error text
|
1 anno fa |
Jeffrey Morgan
|
77a66df72c
add macOS memory check for 47B models
|
1 anno fa |
Jeffrey Morgan
|
5b4837f881
remove unused filetype check
|
1 anno fa |
Jeffrey Morgan
|
29340c2e62
update cmake flags for `amd64` macOS (#1780)
|
1 anno fa |
Daniel Hiltgen
|
d5ec730354
Merge pull request #1779 from dhiltgen/refined_amd_gpu_list
|
1 anno fa |
Daniel Hiltgen
|
8bed487aba
Merge pull request #1778 from dhiltgen/wsl1
|
1 anno fa |
Daniel Hiltgen
|
c1a10a6e9b
Merge pull request #1781 from dhiltgen/cpu_only_build
|
1 anno fa |
Daniel Hiltgen
|
ddbfa6fe31
Fix CPU only builds
|
1 anno fa |
Daniel Hiltgen
|
2fcd41ef81
Fail fast on WSL1 while allowing on WSL2
|
1 anno fa |
Daniel Hiltgen
|
16f4603b67
Improve maintainability of Radeon card list
|
1 anno fa |
Daniel Hiltgen
|
1184686649
Merge pull request #1776 from dhiltgen/render_group
|
1 anno fa |
Daniel Hiltgen
|
2588cb2daa
Add ollama user to render group for Radeon support
|
1 anno fa |
Jeffrey Morgan
|
c7ea8f237e
set `num_gpu` to 1 only by default on darwin arm64 (#1771)
|
1 anno fa |
Bruce MacDonald
|
0b3118e0af
fix: relay request opts to loaded llm prediction (#1761)
|
1 anno fa |
Daniel Hiltgen
|
05face44ef
Merge pull request #1683 from dhiltgen/fix_windows_test
|
1 anno fa |
Daniel Hiltgen
|
a2ad952440
Fix windows system memory lookup
|
1 anno fa |
Daniel Hiltgen
|
5fea4410be
Merge pull request #1680 from dhiltgen/better_patching
|
1 anno fa |
Bruce MacDonald
|
b846eb64d0
Fix `template` api doc description (#1661)
|
1 anno fa |
Cole Gillespie
|
3c5dd9ed1d
Update README.md (#1766)
|
1 anno fa |