Daniel Hiltgen 345420998e Prevent partial loading on mixed GPU brands ...

In mult-brand GPU setups, if we couldn't fully load the model we
would fall through the scheduler and mistakenly try to load across
a mix of brands.  This makes sure we find the set of GPU(s) that
best fit for the partial load.

2024-07-30 11:00:55 -07:00

..

testdata/tools

server: collect nested tool call objects when parsing (#5824)

2024-07-22 12:38:03 -04:00

auth.go

fix nil deref in auth.go

2024-07-26 14:14:48 -07:00

download.go

server: fix race conditions during download (#5994)

2024-07-26 14:24:24 -07:00

fixblobs_test.go

server: replace blob prefix separator from ':' to '-' (#3146)

2024-03-14 20:18:06 -07:00

fixblobs.go

server: replace blob prefix separator from ':' to '-' (#3146)

2024-03-14 20:18:06 -07:00

images.go

server: reuse original download URL for images (#5962)

2024-07-25 15:58:30 -07:00

layer.go

Merge pull request #3718 from ollama/mxyng/modelname-3

2024-05-29 12:02:07 -07:00

manifest_test.go

remove ManifestV2

2024-07-01 10:40:54 -07:00

manifest.go

remove ManifestV2

2024-07-01 10:40:54 -07:00

model_test.go

server: collect nested tool call objects when parsing (#5824)

2024-07-22 12:38:03 -04:00

model.go

Merge pull request #5512 from ollama/mxyng/detect-stop

2024-07-26 13:48:23 -07:00

modelpath_test.go

add OLLAMA_MODELS to envconfig (#5029)

2024-06-13 12:52:03 -07:00

modelpath.go

fix: use envconfig.ModelsDir directly (#4821)

2024-07-03 15:36:11 -07:00

prompt_test.go

add chat and generate tests with mock runner

2024-07-16 09:39:31 -07:00

prompt.go

tools

2024-07-15 15:26:16 -07:00

routes_create_test.go

Merge pull request #5512 from ollama/mxyng/detect-stop

2024-07-26 13:48:23 -07:00

routes_delete_test.go

add chat and generate tests with mock runner

2024-07-16 09:39:31 -07:00

routes_generate_test.go

Fix generate test flakyness (#5804)

2024-07-19 19:11:25 -07:00

routes_list_test.go

add chat and generate tests with mock runner

2024-07-16 09:39:31 -07:00

routes_test.go

server: return empty slice on empty /api/embed request (#5713)

2024-07-15 17:39:44 -07:00

routes.go

fix dupe err message (#5857)

2024-07-22 15:48:15 -07:00

sched_test.go

Prevent partial loading on mixed GPU brands

2024-07-30 11:00:55 -07:00

sched.go

Prevent partial loading on mixed GPU brands

2024-07-30 11:00:55 -07:00

upload.go

fix nil deref in auth.go

2024-07-26 14:14:48 -07:00