mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 02:16:36 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
ollama/server
History
Exact
Daniel Hiltgen 5e380c3b42
sched: fix race leading to orphaned runners (#10599) 
If a model is loading, and the request context is canceled during the load
by a client closing the connection, and another request is inbound for the
same model with a different configuration (context size, etc.) thus requiring
a reload, two unload events can be in flight.  The first shuts down the
original model load, but the second one caused the loss of the new
reloading runner reference, thus triggering the leak.

The primary fix is detecting the duplicate unload and ignoring the second
instance.  The load routine is also hardened to ensure we detect
clobbering an already present runner and unload it with a warning.
2025-05-07 09:38:17 -07:00
..
internal server: remove internal cmd (#10595) 2025-05-06 13:05:01 -07:00
testdata/tools all: fix typos in documentation, code, and comments (#7021) 2024-12-10 12:58:06 -08:00
auth.go fix nil deref in auth.go 2024-07-26 14:14:48 -07:00
create.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
create_test.go server: validate local path on safetensor create (#9379) 2025-02-28 16:10:43 -08:00
download.go server: organize error types (#9465) 2025-03-28 11:50:22 -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 image: add vision capability for projector-based models (#10509) 2025-05-01 16:50:20 -07:00
images_test.go api: return model capabilities from the show endpoint (#10066) 2025-04-01 15:21:46 -07:00
layer.go One corrupt manifest should not wedge model operations (#7515) 2024-11-05 14:21:45 -08:00
manifest.go One corrupt manifest should not wedge model operations (#7515) 2024-11-05 14:21:45 -08:00
manifest_test.go One corrupt manifest should not wedge model operations (#7515) 2024-11-05 14:21:45 -08:00
model.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
model_test.go Update the /api/create endpoint to use JSON (#7935) 2024-12-31 18:02:30 -08:00
modelpath.go server: organize error types (#9465) 2025-03-28 11:50:22 -07:00
modelpath_test.go server: more support for mixed-case model names (#8017) 2024-12-11 15:29:59 -08:00
prompt.go gemma3: Allow multiple image in a single input 2025-03-14 15:38:54 -07:00
prompt_test.go prompt: Don't trim whitespace from prompts 2024-12-09 11:02:55 -08:00
quantization.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
quantization_test.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
routes.go server: send 405 instead of 404 for unallowed methods (#10275) 2025-05-06 14:45:37 -07:00
routes_create_test.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
routes_delete_test.go Update the /api/create endpoint to use JSON (#7935) 2024-12-31 18:02:30 -08:00
routes_generate_test.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
routes_list_test.go Update the /api/create endpoint to use JSON (#7935) 2024-12-31 18:02:30 -08:00
routes_test.go api: remove unused RetrieveModelResponse type (#10603) 2025-05-06 23:08:03 -07:00
sched.go sched: fix race leading to orphaned runners (#10599) 2025-05-07 09:38:17 -07:00
sched_test.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
sparse_common.go Don't hard fail on sparse setup error 2024-08-09 12:16:19 -07:00
sparse_windows.go Don't hard fail on sparse setup error 2024-08-09 12:16:19 -07:00
upload.go server: always print upload/download part info (#8832) 2025-02-04 19:30:49 -08:00