ollama/server
Daniel Hiltgen 3c75113e37 Prevent loading models larger than total memory
Users may not realize the siny new model they're trying to load
fits on their disk, but can't load into system+GPU memory.  Today
we crash, but with this fix, we'll give them a better error message
before even trying to load it.
2024-07-03 14:47:42 -07:00
..
auth.go Revert "use post token" 2024-05-11 22:19:14 -07:00
download.go server: skip blob verification for already verified blobs 2024-06-05 16:39:11 -07:00
fixblobs.go server: replace blob prefix separator from ':' to '-' (#3146) 2024-03-14 20:18:06 -07:00
fixblobs_test.go server: replace blob prefix separator from ':' to '-' (#3146) 2024-03-14 20:18:06 -07:00
images.go use kvs to detect embedding models 2024-07-01 10:47:43 -07:00
layer.go Merge pull request #3718 from ollama/mxyng/modelname-3 2024-05-29 12:02:07 -07:00
manifest.go remove ManifestV2 2024-07-01 10:40:54 -07:00
manifest_test.go remove ManifestV2 2024-07-01 10:40:54 -07:00
model.go Merge pull request #5051 from ollama/mxyng/capabilities 2024-07-02 14:26:07 -07:00
model_test.go err on insecure path 2024-07-01 15:55:59 -07:00
modelpath.go add OLLAMA_MODELS to envconfig (#5029) 2024-06-13 12:52:03 -07:00
modelpath_test.go add OLLAMA_MODELS to envconfig (#5029) 2024-06-13 12:52:03 -07:00
prompt.go rename templates to template 2024-07-01 10:40:54 -07:00
prompt_test.go rename templates to template 2024-07-01 10:40:54 -07:00
routes.go fix generate template 2024-07-02 16:42:17 -07:00
routes_create_test.go add OLLAMA_MODELS to envconfig (#5029) 2024-06-13 12:52:03 -07:00
routes_delete_test.go add OLLAMA_MODELS to envconfig (#5029) 2024-06-13 12:52:03 -07:00
routes_list_test.go add OLLAMA_MODELS to envconfig (#5029) 2024-06-13 12:52:03 -07:00
routes_test.go OpenAI: /v1/models and /v1/models/{model} compatibility (#5007) 2024-07-02 11:50:56 -07:00
sched.go Prevent loading models larger than total memory 2024-07-03 14:47:42 -07:00
sched_test.go Prevent loading models larger than total memory 2024-07-03 14:47:42 -07:00
upload.go lint 2024-06-04 11:13:30 -07:00