release: v0.2.31 - O(1) attention knobs, reasoning toggle & admin token persistence

This commit is contained in:
infosave2007
2026-07-22 11:12:40 +03:00
parent 94c8551206
commit 1414ad1b52
10 changed files with 140 additions and 43 deletions
+3
View File
@@ -1336,6 +1336,9 @@ async fn register_import(State(state): State<SharedState>, Path(job): Path<Strin
think_budget: None,
system_prompt: None,
o1: None,
o1_m: None,
o1_window: None,
o1_sink: None,
skip_mtp: false,
});
} else {
+17 -3
View File
@@ -293,13 +293,27 @@ fn spawn_serve(server: &CmfServer, cfg: &CmfCfg) -> Result<Child, String> {
if server.gpu {
cmd.env("CMF_GPU", "1");
}
// O(1) Nyström attention: layers spec + sub-parameters.
if let Some(o1) = &server.o1 {
if !o1.trim().is_empty() && o1 != "off" {
cmd.arg("--o1").arg(o1);
let s = o1.trim();
if !s.is_empty() {
// Pass even "off" so it explicitly overrides a file converter hint.
cmd.arg("--o1").arg(s);
}
}
if let Some(m) = server.o1_m {
cmd.arg("--o1-m").arg(m.to_string());
}
if let Some(w) = server.o1_window {
cmd.arg("--o1-window").arg(w.to_string());
}
if let Some(sink) = server.o1_sink {
cmd.arg("--o1-sink").arg(sink.to_string());
}
// MTP (Multi-Token Prediction) speculative decoding: the engine reads
// CMF_MTP env; "0" disables. There is no CLI flag for this.
if server.skip_mtp {
cmd.arg("--skip-mtp");
cmd.env("CMF_MTP", "0");
}
cmd.stdout(Stdio::null())
.stderr(Stdio::null())
+19 -4
View File
@@ -98,10 +98,19 @@ pub struct CmfServer {
/// Default system prompt prepended if request lacks one.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub system_prompt: Option<String>,
/// O(1) constant-memory streaming attention hint (all, deep, custom, off).
/// O(1) Nyström attention layer spec (all | deepN | i,j,k | off).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub o1: Option<String>,
/// Skip Multi-Token Prediction (MTP) heads.
/// O(1) landmark budget (default 32; ≥4).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub o1_m: Option<u32>,
/// O(1) exact-window width (default 128).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub o1_window: Option<u32>,
/// O(1) permanent exact sink keys (default 4, StreamingLLM discipline).
#[serde(default, skip_serializing_if = "Option::is_none")]
pub o1_sink: Option<u32>,
/// Disable Multi-Token Prediction speculative decoding (CMF_MTP=0).
#[serde(default)]
pub skip_mtp: bool,
}
@@ -199,6 +208,9 @@ impl CmfCfg {
think_budget: None,
system_prompt: None,
o1: None,
o1_m: None,
o1_window: None,
o1_sink: None,
skip_mtp: false,
}];
}
@@ -510,10 +522,12 @@ pub struct AdminCfg {
/// Whether the admin panel and admin API (`/admin`, `/admin/api/*`) are enabled.
#[serde(default = "default_admin_enabled")]
pub enabled: bool,
/// Name of the env variable holding the admin token. If unset (or empty),
/// a token is generated at startup and printed to the log.
/// Name of the env variable holding the admin token.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub token_env: Option<String>,
/// Persistent admin token configured directly in toml.
#[serde(default, skip_serializing_if = "Option::is_none")]
pub token: Option<String>,
/// Optional separate bind address for the admin surface (e.g. `127.0.0.1:9001`).
/// If unset, the admin interface lives on the main `listen` address under `/admin`.
#[serde(default, skip_serializing_if = "Option::is_none")]
@@ -524,6 +538,7 @@ impl Default for AdminCfg {
Self {
enabled: default_admin_enabled(),
token_env: None,
token: None,
listen: None,
}
}
+5
View File
@@ -61,6 +61,11 @@ fn resolve_admin_token(cfg: &Config, args: &Args) -> (String, bool) {
return (t.clone(), false);
}
}
if let Some(t) = &cfg.admin.token {
if !t.is_empty() {
return (t.clone(), false);
}
}
(admin::random_token(24), true)
}