pali112
/
ollama
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ollama/server
History
Jesse Gross d897a54f08
server: Reduce gpt-oss context length for small VRAM GPUs 
gpt-oss works best with a context length of at least 8k. However,
for GPUs with limited amount of VRAM, there is a significant
performance hit to this increased context. In these cases, we
switch to the Ollama default of 4k
 		2025-12-29 06:39:50 -06:00
..
internal cache: fix comment function name in cache.go (#11110) 2025-12-29 06:38:16 -06:00
auth.go fix nil deref in auth.go 2024-07-26 14:14:48 -07:00
create.go remove support for multiple ggufs in a single file (#10722) 2025-12-29 06:38:05 -06:00
create_test.go server: validate local path on safetensor create (#9379) 2025-02-28 16:10:43 -08:00
download.go server: abort download on empty digest 2025-12-29 06:38:09 -06:00
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
harmonyparser.go gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
harmonyparser_test.go gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
images.go gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
images_test.go Reapply "feat: incremental gguf parser (#10822)" (#11114) (#11119) 2025-12-29 06:38:17 -06:00
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 tools: refactor tool call parsing and enable streaming (#10415) 2025-12-29 06:38:07 -06:00
modelpath.go server: add hint to the error message when model path access fails (#10843) 2025-12-29 06:38:07 -06:00
modelpath_test.go lint: enable usetesting, disable tenv (#10594) 2025-12-29 06:37:55 -06:00
prompt.go gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
prompt_test.go gpt-oss (#11672) 2025-12-29 06:39:48 -06:00
quantization.go skip quantizing per_layer_token_embd (#11207) 2025-12-29 06:39:38 -06:00
quantization_test.go Reapply "feat: incremental gguf parser (#10822)" (#11114) (#11119) 2025-12-29 06:38:17 -06:00
routes.go server: Reduce gpt-oss context length for small VRAM GPUs 2025-12-29 06:39:50 -06:00
routes_create_test.go Move quantization to new backend (#10363) 2025-12-29 06:37:52 -06:00
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 tools: support anyOf types 2025-12-29 06:39:49 -06:00
routes_harmony_streaming_test.go tools: support anyOf types 2025-12-29 06:39:49 -06:00
routes_list_test.go Update the /api/create endpoint to use JSON (#7935) 2024-12-31 18:02:30 -08:00
routes_test.go server: use slices.Equal to simplify code (#11502) 2025-12-29 06:39:45 -06:00
sched.go Reduce default parallelism to 1 (#11330) 2025-12-29 06:39:41 -06:00
sched_test.go Reapply "feat: incremental gguf parser (#10822)" (#11114) (#11119) 2025-12-29 06:38:17 -06:00
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