hugo/DS4Server
1
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity

Load GLM vision weights on demand

Browse Source
This commit is contained in:
Georg Bauer
2026-09-01 20:08:36 +02:00
parent 46d6a976a5
commit ee515ee824
10 changed files with 293 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
src/app/view/preferences.rs
View File

@@ -24,6 +24,9 @@ impl App {
.acceleration_model
.supports_glm_mtp()
.then_some(Message::PreferenceGlmMtpTimingChanged);
let keep_vision_loaded_toggle: Option<fn(bool) -> Message> =
(self.preference_draft.acceleration_model == ModelChoice::Glm53Flash)
.then_some(Message::PreferenceKeepVisionLoadedChanged);
let dspark_strict_toggle: Option<fn(bool) -> Message> = self
.preference_draft
.acceleration_model
@@ -615,6 +618,12 @@ impl App {
.on_toggle_maybe(glm_mtp_timing_toggle),
"Records per-stage timings of the speculative path to the log, to show where the acceleration actually goes. A diagnostic aid that costs a little throughput.",
),
hint(
toggle(self.preference_draft.keep_vision_loaded)
.label("Keep GLM 5.3 vision weights loaded")
.on_toggle_maybe(keep_vision_loaded_toggle),
"Keeps the vision encoder mapped between image turns for lower image latency. Off releases it after encoding all images in a turn, leaving more memory for long text contexts.",
),
dspark,
preference_input_row(
"DSpark confidence threshold",