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

16
src/settings.rs
View File

@@ -34,8 +34,8 @@ impl SpeculativePreferences {
if self.glm_mtp_timing && !self.glm_mtp {
return Err("GLM MTP timing requires GLM MTP.".into());
}
if model != ModelChoice::Glm52 && (self.glm_mtp || self.glm_mtp_timing) {
return Err("GLM MTP is available only for GLM 5.2.".into());
if !model.supports_glm_mtp() && (self.glm_mtp || self.glm_mtp_timing) {
return Err("GLM MTP is available only for GLM models.".into());
}
if self.dspark_enabled && !model.supports_dspark() {
return Err("DSpark is not available for the selected model.".into());
@@ -166,8 +166,8 @@ impl SsdPreferences {
{
return Err("SSD full-layer count is too large.".into());
}
if self.full_layers.is_some_and(|layers| layers > 0) && model != ModelChoice::Glm52 {
return Err("Fully resident SSD layers are available only for GLM 5.2.".into());
if self.full_layers.is_some_and(|layers| layers > 0) && !model.is_glm() {
return Err("Fully resident SSD layers are available only for GLM models.".into());
}
if let Some(StreamingCacheBudget::Gib(gib)) = self.cache {
validate_gib("SSD cache budget", gib)?;
@@ -443,12 +443,12 @@ impl ExecutionPreferences {
{
return Err("Prefill chunk is too large.".into());
}
if model == ModelChoice::Glm52 {
if model.is_glm() {
if self.power_percent.is_some_and(|power| power != 100) {
return Err("GLM 5.2 currently requires 100% GPU power.".into());
return Err("GLM currently requires 100% GPU power.".into());
}
if self.prefill_chunk.is_some() {
return Err("GLM 5.2 selects its prefill chunk automatically.".into());
return Err("GLM selects its prefill chunk automatically.".into());
}
}
Ok(())
@@ -569,7 +569,7 @@ impl GenerationPreferences {
model: ModelChoice,
kv_cache: KvCacheSettings,
) -> TurnSettings {
let glm = model == ModelChoice::Glm52;
let glm = model.is_glm();
TurnSettings {
kv_cache,
context_tokens: self.context_tokens,