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

Add GLM 5.3 Flash support

Browse Source
This commit is contained in:
Georg Bauer
2026-09-01 19:06:20 +02:00
parent 9a33c61ea6
commit 46d6a976a5
31 changed files with 7806 additions and 447 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
src/app/view/preferences.rs
View File

@@ -14,12 +14,16 @@ impl App {
.on_toggle_maybe(dspark_toggle),
"Speculative decoding with the managed DSpark draft artifact: a small model proposes tokens that the main model verifies in one pass. Usually a large speedup; the target model may also stream routed experts from SSD.",
);
let glm_mtp_toggle: Option<fn(bool) -> Message> =
(self.preference_draft.acceleration_model == ModelChoice::Glm52)
.then_some(Message::PreferenceGlmMtpChanged);
let glm_mtp_timing_toggle: Option<fn(bool) -> Message> =
(self.preference_draft.acceleration_model == ModelChoice::Glm52)
.then_some(Message::PreferenceGlmMtpTimingChanged);
let glm_mtp_toggle: Option<fn(bool) -> Message> = self
.preference_draft
.acceleration_model
.supports_glm_mtp()
.then_some(Message::PreferenceGlmMtpChanged);
let glm_mtp_timing_toggle: Option<fn(bool) -> Message> = self
.preference_draft
.acceleration_model
.supports_glm_mtp()
.then_some(Message::PreferenceGlmMtpTimingChanged);
let dspark_strict_toggle: Option<fn(bool) -> Message> = self
.preference_draft
.acceleration_model
@@ -71,14 +75,16 @@ impl App {
"0.8 (DeepSeek V4 Flash default)",
&self.preference_draft.dspark_confidence_threshold,
);
if self.preference_draft.model != ModelChoice::Glm52 {
if !self.preference_draft.model.is_glm() {
power = power.on_input(Message::PreferencePowerChanged);
prefill = prefill.on_input(Message::PreferencePrefillChunkChanged);
}
if self.preference_draft.model != ModelChoice::Glm52 {
steering_file = steering_file.on_input(Message::PreferenceSteeringFileChanged);
steering_ffn = steering_ffn.on_input(Message::PreferenceSteeringFfnChanged);
steering_attn = steering_attn.on_input(Message::PreferenceSteeringAttnChanged);
}
if self.preference_draft.acceleration_model == ModelChoice::Glm52 {
if self.preference_draft.acceleration_model.is_glm() {
ssd_full_layers = ssd_full_layers.on_input(Message::PreferenceSsdFullLayersChanged);
}
if self.preference_draft.acceleration_model.supports_dspark() {
@@ -467,6 +473,12 @@ impl App {
text_input("32768", &self.preference_draft.context_tokens)
.on_input(Message::PreferenceContextChanged),
),
text(if self.preference_draft.generation_model == ModelChoice::Glm53Flash {
"GLM 5.3 Flash: 32768 is the recommended default on this 128 GB machine; 50000 is the validated extended-session target."
} else {
""
})
.size(12),
preference_input_row(
"Maximum generated tokens",
"Hard stop for a single reply, counted from the first generated token. It bounds runaway answers and reasoning loops; it does not reserve memory.",
@@ -550,8 +562,8 @@ impl App {
.on_toggle(Message::PreferenceWarmWeightsChanged),
"Reads every mapped weight page once at load, so the first reply is not interrupted by page faults from disk. Loading takes longer and memory pressure rises immediately.",
),
text(if self.preference_draft.model == ModelChoice::Glm52 {
"GLM 5.2 uses full GPU power and selects prefill chunks automatically."
text(if self.preference_draft.model.is_glm() {
"GLM uses full GPU power and selects prefill chunks automatically."
} else {
"Blank numeric values preserve DS4's automatic engine behavior."
})
@@ -595,7 +607,7 @@ impl App {
toggle(self.preference_draft.glm_mtp)
.label("Enable integrated GLM MTP")
.on_toggle_maybe(glm_mtp_toggle),
"Uses the prediction head built into GLM 5.2 for speculative decoding, so no separate draft model is loaded. Available for GLM 5.2 only.",
"Uses the prediction head built into GLM for speculative decoding, so no separate draft model is loaded.",
),
hint(
toggle(self.preference_draft.glm_mtp_timing)
@@ -623,7 +635,7 @@ impl App {
),
text(if self.preference_draft.acceleration_model.supports_dspark() {
"DeepSeek V4 Flash 0731 uses its managed DSpark support artifact."
} else if self.preference_draft.acceleration_model == ModelChoice::Glm52 {
} else if self.preference_draft.acceleration_model.supports_glm_mtp() {
"GLM MTP is integrated; DSpark is unavailable for this model."
} else {
"No speculative-decoding support is available for this model."