Louis 2899d58ad7

🐛fix: llama.cpp default NGL setting does not offload all layers to GPU (#5310) ...

* 🐛fix: llama.cpp default NGL setting does not offload all layers to GPU

* chore: cover more cases

* chore: clean up

* fix: should not show GPU section on Mac

2025-06-17 15:30:07 +07:00

..

assistant-extension

Merge pull request #5262 from menloresearch/chore/sync-new-hub-data

2025-06-13 17:05:49 +07:00

conversational-extension

chore: allow users to enable/disable MCP servers (#5015)

2025-05-19 13:15:37 +07:00

download-extension

🐛fix: default onboarding model should use recommended quantizations (#5273)

2025-06-15 02:34:14 +07:00

engine-management-extension

fix: clean up cortex processes (#5215)

2025-06-09 22:23:07 +07:00

hardware-management-extension

chore: add relocate jan data folder function to new FE (#5043)

2025-05-21 10:48:10 +07:00

inference-cortex-extension

🐛fix: llama.cpp default NGL setting does not offload all layers to GPU (#5310)

2025-06-17 15:30:07 +07:00

model-extension

🐛fix: Jan-nano repo name changed (#5274)

2025-06-15 11:17:41 +07:00

.yarnrc.yml

chore: upgrade to turbo v2 and reduce ci quality gate runtime (#4324)

2024-12-29 17:46:15 +07:00

package.json

chore: upgrade to turbo v2 and reduce ci quality gate runtime (#4324)

2024-12-29 17:46:15 +07:00

yarn.lock

epic: Jan with new UI/UX (#4964)

2025-05-15 19:38:59 +07:00