github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-03-08 23:04:13 -05:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
ollama/app/server
History
Jeffrey Morgan fa6c0127e6 app: expose server's default context length to UI (#14037) 
Parse the default_num_ctx from the server's "vram-based default context"
log line and expose it through the inference compute API. This eliminates
duplicate VRAM tier calculation logic in the frontend.

- Add InferenceInfo struct with Computes and DefaultContextLength
- Rename GetInferenceComputer to GetInferenceInfo
- Handle missing default context line gracefully (older servers)
- Add DefaultContextLength to InferenceComputeResponse
- Update Settings UI to use server's default, disable slider while loading
- Add disabled prop to Slider component (grays out + hides handle)
- Migrate existing users with context_length=4096 to 0 (auto mode)
2026-02-20 18:56:30 -08:00
..
server_test.go
app: expose server's default context length to UI (#14037)
2026-02-20 18:56:30 -08:00
server_unix.go
app: add code for macOS and Windows apps under 'app' (#12933)
2025-11-04 11:40:17 -08:00
server_windows.go
app: add code for macOS and Windows apps under 'app' (#12933)
2025-11-04 11:40:17 -08:00
server.go
app: expose server's default context length to UI (#14037)
2026-02-20 18:56:30 -08:00