feat: more preferences
This commit is contained in:
Georg Bauer
211
src/app/view.rs
211
src/app/view.rs
@@ -3,7 +3,7 @@ use crate::database::{ProjectWithSessions, Session};
|
||||
use crate::model::{
|
||||
self, DownloadPhase, MODEL_CHOICES, ManagedArtifact, ManagedArtifactState, ModelChoice,
|
||||
};
|
||||
use crate::settings::REASONING_MODES;
|
||||
use crate::settings::{GIB, REASONING_MODES};
|
||||
use iced::theme::{Palette, palette};
|
||||
use iced::widget::{
|
||||
Button, Space, Svg, button, checkbox, column, container, horizontal_rule, opaque, pick_list,
|
||||
@@ -300,21 +300,58 @@ impl App {
|
||||
self.preference_draft.dspark_enabled,
|
||||
)
|
||||
.on_toggle_maybe(dspark_toggle);
|
||||
let glm_mtp_toggle: Option<fn(bool) -> Message> = (self.preference_draft.model
|
||||
== ModelChoice::Glm52)
|
||||
.then_some(Message::PreferenceGlmMtpChanged);
|
||||
let glm_mtp_timing_toggle: Option<fn(bool) -> Message> = (self.preference_draft.model
|
||||
== ModelChoice::Glm52)
|
||||
.then_some(Message::PreferenceGlmMtpTimingChanged);
|
||||
let dspark_strict_toggle: Option<fn(bool) -> Message> = self
|
||||
.preference_draft
|
||||
.model
|
||||
.supports_dspark()
|
||||
.then_some(Message::PreferenceDsparkStrictChanged);
|
||||
let effective = self
|
||||
.preference_draft
|
||||
.generation()
|
||||
.ok()
|
||||
.map(|generation| generation.effective(self.preference_draft.model));
|
||||
let execution = self
|
||||
.map(|generation| generation.turn_settings(self.preference_draft.model));
|
||||
let engine = self
|
||||
.preference_draft
|
||||
.execution()
|
||||
.runtime()
|
||||
.ok()
|
||||
.map(|execution| execution.engine_settings());
|
||||
.and_then(|runtime| runtime.engine_settings(self.preference_draft.model).ok());
|
||||
let artifacts = model::engine_artifacts(
|
||||
self.preference_draft.model,
|
||||
self.preference_draft.dspark_enabled,
|
||||
&models_path(),
|
||||
);
|
||||
let mut power = text_input("100", &self.preference_draft.power_percent);
|
||||
let mut prefill = text_input("Automatic", &self.preference_draft.prefill_chunk);
|
||||
let mut ssd_full_layers = text_input("Automatic", &self.preference_draft.ssd_full_layers);
|
||||
let mut steering_file = text_input(
|
||||
"Direction-vector file path",
|
||||
&self.preference_draft.directional_steering_file,
|
||||
);
|
||||
let mut steering_ffn =
|
||||
text_input("Automatic", &self.preference_draft.directional_steering_ffn);
|
||||
let mut steering_attn = text_input("0", &self.preference_draft.directional_steering_attn);
|
||||
let mut dspark_confidence = text_input(
|
||||
"0.9 (DS4 default)",
|
||||
&self.preference_draft.dspark_confidence_threshold,
|
||||
);
|
||||
if self.preference_draft.model != ModelChoice::Glm52 {
|
||||
power = power.on_input(Message::PreferencePowerChanged);
|
||||
prefill = prefill.on_input(Message::PreferencePrefillChunkChanged);
|
||||
steering_file = steering_file.on_input(Message::PreferenceSteeringFileChanged);
|
||||
steering_ffn = steering_ffn.on_input(Message::PreferenceSteeringFfnChanged);
|
||||
steering_attn = steering_attn.on_input(Message::PreferenceSteeringAttnChanged);
|
||||
} else {
|
||||
ssd_full_layers = ssd_full_layers.on_input(Message::PreferenceSsdFullLayersChanged);
|
||||
}
|
||||
if self.preference_draft.model.supports_dspark() {
|
||||
dspark_confidence =
|
||||
dspark_confidence.on_input(Message::PreferenceDsparkConfidenceChanged);
|
||||
}
|
||||
|
||||
let mut fields = column![
|
||||
@@ -325,12 +362,14 @@ impl App {
|
||||
Message::PreferenceModelChanged,
|
||||
)
|
||||
.width(Length::Fill),
|
||||
dspark,
|
||||
text(if self.preference_draft.model.supports_dspark() {
|
||||
"DSpark support is used only when enabled. Downloads are managed in Model Manager."
|
||||
} else {
|
||||
"DSpark is not available for the selected model."
|
||||
})
|
||||
text(format!(
|
||||
"Main: {}{}",
|
||||
artifacts.model.display(),
|
||||
artifacts
|
||||
.mtp
|
||||
.as_ref()
|
||||
.map_or_else(String::new, |path| format!(" • support: {}", path.display())),
|
||||
))
|
||||
.size(12),
|
||||
Space::with_height(8),
|
||||
text("EXECUTION").size(11),
|
||||
@@ -351,16 +390,136 @@ impl App {
|
||||
"Blank numeric values preserve DS4's automatic engine behavior."
|
||||
})
|
||||
.size(12),
|
||||
text(execution.map_or_else(
|
||||
text(engine.as_ref().map_or_else(
|
||||
|| "Effective execution settings will appear after valid values are entered."
|
||||
.to_owned(),
|
||||
|settings| format!(
|
||||
|engine| {
|
||||
let settings = engine.execution;
|
||||
format!(
|
||||
"Metal engine: threads {} • power {}% • prefill {} • quality {} • warm weights {}",
|
||||
if settings.cpu_threads == 0 { "auto".to_owned() } else { settings.cpu_threads.to_string() },
|
||||
if settings.power_percent == 0 { 100 } else { settings.power_percent },
|
||||
if settings.prefill_chunk == 0 { "auto".to_owned() } else { settings.prefill_chunk.to_string() },
|
||||
if settings.quality { "on" } else { "off" },
|
||||
if settings.warm_weights { "on" } else { "off" },
|
||||
)},
|
||||
))
|
||||
.size(12),
|
||||
Space::with_height(8),
|
||||
text("SPECULATIVE DECODING").size(11),
|
||||
preference_input_row(
|
||||
"MTP draft tokens",
|
||||
text_input("1", &self.preference_draft.mtp_draft_tokens)
|
||||
.on_input(Message::PreferenceMtpDraftChanged),
|
||||
),
|
||||
preference_input_row(
|
||||
"MTP verifier margin",
|
||||
text_input("3", &self.preference_draft.mtp_margin)
|
||||
.on_input(Message::PreferenceMtpMarginChanged),
|
||||
),
|
||||
checkbox("Enable integrated GLM MTP", self.preference_draft.glm_mtp)
|
||||
.on_toggle_maybe(glm_mtp_toggle),
|
||||
checkbox(
|
||||
"Log GLM MTP timing counters",
|
||||
self.preference_draft.glm_mtp_timing,
|
||||
)
|
||||
.on_toggle_maybe(glm_mtp_timing_toggle),
|
||||
dspark,
|
||||
preference_input_row("DSpark confidence threshold", dspark_confidence),
|
||||
checkbox(
|
||||
"DSpark target-only decode",
|
||||
self.preference_draft.dspark_strict,
|
||||
)
|
||||
.on_toggle_maybe(dspark_strict_toggle),
|
||||
text(if self.preference_draft.model.supports_dspark() {
|
||||
"DSpark uses the managed support artifact; entering a threshold or enabling strict mode also enables DSpark."
|
||||
} else if self.preference_draft.model == ModelChoice::Glm52 {
|
||||
"GLM MTP is integrated; DSpark is unavailable for this model."
|
||||
} else {
|
||||
"No managed MTP support artifact is available for this model."
|
||||
})
|
||||
.size(12),
|
||||
text(engine.as_ref().map_or_else(
|
||||
|| "Effective speculative settings will appear after valid values are entered."
|
||||
.to_owned(),
|
||||
|engine| {
|
||||
let settings = engine.speculative;
|
||||
format!(
|
||||
"Engine: MTP draft {} • margin {} • GLM MTP {} • timing {} • DSpark {} • confidence {}{} • target-only {}",
|
||||
settings.mtp_draft_tokens,
|
||||
settings.mtp_margin,
|
||||
if settings.glm_mtp { "on" } else { "off" },
|
||||
if settings.glm_mtp_timing { "on" } else { "off" },
|
||||
if settings.dspark { "on" } else { "off" },
|
||||
settings.dspark_confidence_threshold,
|
||||
if settings.dspark_confidence_threshold_set { " explicit" } else { " default" },
|
||||
if settings.dspark_strict { "on" } else { "off" },
|
||||
)},
|
||||
))
|
||||
.size(12),
|
||||
Space::with_height(8),
|
||||
text("SSD STREAMING").size(11),
|
||||
checkbox("Enable SSD-backed model streaming", self.preference_draft.ssd_streaming)
|
||||
.on_toggle(Message::PreferenceSsdChanged),
|
||||
checkbox("Skip automatic expert preload", self.preference_draft.ssd_streaming_cold)
|
||||
.on_toggle(Message::PreferenceSsdColdChanged),
|
||||
preference_input_row(
|
||||
"Expert cache count or GiB",
|
||||
text_input("Automatic, 128, or 64GB", &self.preference_draft.ssd_cache)
|
||||
.on_input(Message::PreferenceSsdCacheChanged),
|
||||
),
|
||||
preference_input_row("Fully resident GLM layers", ssd_full_layers),
|
||||
preference_input_row(
|
||||
"Explicit expert preload count",
|
||||
text_input("Automatic", &self.preference_draft.ssd_preload_experts)
|
||||
.on_input(Message::PreferenceSsdPreloadChanged),
|
||||
),
|
||||
text("A blank full-layer value is automatic; an explicit 0 disables fully resident GLM layers. SSD streaming and DSpark are mutually exclusive.")
|
||||
.size(12),
|
||||
text(engine.as_ref().map_or_else(
|
||||
|| "Effective SSD settings will appear after valid values are entered."
|
||||
.to_owned(),
|
||||
|engine| {
|
||||
let settings = engine.ssd;
|
||||
let cache = if settings.cache_bytes > 0 {
|
||||
format!("{} GiB", settings.cache_bytes / GIB)
|
||||
} else if settings.cache_experts > 0 {
|
||||
format!("{} experts", settings.cache_experts)
|
||||
} else {
|
||||
"auto".to_owned()
|
||||
};
|
||||
format!(
|
||||
"Engine: streaming {} • cold {} • cache {} • full layers {}{} • preload {}",
|
||||
if settings.enabled { "on" } else { "off" },
|
||||
if settings.cold { "on" } else { "off" },
|
||||
cache,
|
||||
settings.full_layers,
|
||||
if settings.full_layers_set { " explicit" } else { " auto" },
|
||||
if settings.preload_experts == 0 { "auto".to_owned() } else { settings.preload_experts.to_string() },
|
||||
)
|
||||
},
|
||||
))
|
||||
.size(12),
|
||||
Space::with_height(8),
|
||||
text("DIRECTIONAL STEERING").size(11),
|
||||
text("Direction-vector file").size(13),
|
||||
steering_file.padding(9),
|
||||
preference_input_row("FFN scale", steering_ffn),
|
||||
preference_input_row("Attention scale", steering_attn),
|
||||
text(if self.preference_draft.model == ModelChoice::Glm52 {
|
||||
"Directional steering is not supported for GLM 5.2."
|
||||
} else {
|
||||
"With a file and no explicit scale, DS4 defaults the FFN scale to 1. Scales accept -100 through 100."
|
||||
})
|
||||
.size(12),
|
||||
text(engine.as_ref().map_or_else(
|
||||
|| "Effective steering settings will appear after valid values are entered."
|
||||
.to_owned(),
|
||||
|engine| format!(
|
||||
"Engine: file {} • FFN scale {} • attention scale {}",
|
||||
if engine.steering.file.is_some() { "set" } else { "off" },
|
||||
engine.steering.ffn_scale,
|
||||
engine.steering.attention_scale,
|
||||
),
|
||||
))
|
||||
.size(12),
|
||||
@@ -434,6 +593,32 @@ impl App {
|
||||
))
|
||||
.size(12),
|
||||
Space::with_height(8),
|
||||
text("ADVANCED DIAGNOSTICS").size(11),
|
||||
preference_input_row(
|
||||
"Simulated used memory (GiB)",
|
||||
text_input("Disabled", &self.preference_draft.simulated_used_memory_gib)
|
||||
.on_input(Message::PreferenceSimulatedMemoryChanged),
|
||||
),
|
||||
text("Routed expert profile output").size(13),
|
||||
text_input("Output file path", &self.preference_draft.expert_profile_path)
|
||||
.on_input(Message::PreferenceExpertProfileChanged)
|
||||
.padding(9),
|
||||
text(engine.as_ref().map_or_else(
|
||||
|| "Effective diagnostic settings will appear after valid values are entered."
|
||||
.to_owned(),
|
||||
|engine| format!(
|
||||
"{} load: simulated memory {} • expert profile {}",
|
||||
engine.model,
|
||||
if engine.diagnostics.simulated_used_memory_bytes == 0 {
|
||||
"off".to_owned()
|
||||
} else {
|
||||
format!("{} GiB", engine.diagnostics.simulated_used_memory_bytes / GIB)
|
||||
},
|
||||
if engine.diagnostics.expert_profile_path.is_some() { "set" } else { "off" },
|
||||
),
|
||||
))
|
||||
.size(12),
|
||||
Space::with_height(8),
|
||||
text("INACTIVITY").size(11),
|
||||
row![
|
||||
text_input("10", &self.preference_draft.idle_timeout_minutes)
|
||||
|
||||
Reference in New Issue
Block a user