chore(release): v0.2.27 — auto-spawn local CMF server on model registration

CHANGELOG.md

@@ -3,8 +3,28 @@
 All notable changes to this project are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/).
 
+## [0.2.27] - 2026-07-21
+
+### Fixed
+- **Automatic CMF Local Server Lifecycle**: Registering an imported `.cmf` model automatically adds it to `[[cmf.servers]]` and reloads the runtime (`cmf_runtime::manage`), automatically spawning `cortiq serve` on port 8090 so chat completion requests route seamlessly without `upstream unavailable` errors.
+
+
+### Fixed
+- **Multi-GB Ready CMF Download Stream**: Replaced HTTP stream decoder with a streaming process downloader (`curl`) for pre-converted `.cmf` models to support multi-gigabyte Hugging Face LFS repositories without 30s/60s socket timeouts.
+- **Ready CMF Quantization & UI Labels**: Set correct quantization badges (`Q1`, `Q1T`) for featured ready-to-run `.cmf` models and removed misleading "converting" log messages for direct downloads.
+
+
+### Fixed
+- **Direct Ready CMF Download**: Importing pre-converted `.cmf` model repositories (e.g. `infosave/Bonsai-8B_2bit_cmf`) directly streams the ready `.cmf` file from Hugging Face instead of attempting a safetensors conversion without `config.json`.
+
+
+### Added
+- **New Quantization Schemes**: Added support for `Q4_TILED` (q4t), `Q1T` (1.58-bit ternary), `Q1S` (1-bit sparse), `Q1P` (1-bit PTQ error diffusion), and `Q1` (pure binary) in converter backend and web admin UI.
+- **Featured Ready-to-Run .cmf Models**: Added 1-tap download cards for pre-converted `.cmf` models (`infosave/Bonsai-1.7Bcmf`, `infosave/Bonsai-8B_2bit_cmf`, `infosave/Bonsai-27Bcmf`).
+
 ## [Unreleased]
 
+
 ### Added
 - **Docker Compose** quickstart (`docker-compose.yml` + `config/gateway.compose.toml`):
   gateway + a local Ollama model in one command. GHCR badge in the READMEs.

Cargo.lock

@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "cortiq-gateway"
-version = "0.2.15"
+version = "0.2.27"
 dependencies = [
  "anyhow",
  "arc-swap",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.15"
+version = "0.2.27"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"

src/admin/mod.rs

@@ -1319,6 +1319,18 @@ async fn register_import(State(state): State<SharedState>, Path(job): Path<Strin
         api_key_env: None,
         caps: Vec::new(),
     });
+    if cfg.cmf.manage_server {
+        let port = cfg.cmf.local_port;
+        if !cfg.cmf.servers.iter().any(|s| s.model == j.output) {
+            cfg.cmf.servers.push(crate::config::CmfServer {
+                id: id.clone(),
+                model: j.output.clone(),
+                port,
+                threads: cfg.cmf.threads,
+                gpu: cfg.cmf.gpu,
+            });
+        }
+    }
     state.reload(cfg)?;
     ok(json!({ "ok": true, "model_id": id }))
 }

src/import.rs

@@ -260,14 +260,151 @@ fn sanitize(s: &str) -> String {
 /// Map the UI quant label to the native `cortiq` quant flag.
 fn map_quant(q: &str) -> &'static str {
     match q.to_ascii_uppercase().as_str() {
+        s if s.starts_with("Q4T") || s == "Q4_TILED" => "q4t",
         s if s.starts_with("Q4") => "q4",
-        "Q8_2F" => "q8_2f",
+        "Q8_2F" | "Q82F" => "q8_2f",
         "F16" | "FP16" => "f16",
         "VBIT" => "vbit",
+        "Q1" => "q1",
+        "Q1P" | "Q1_PTQ" => "q1p",
+        "Q1S" | "Q1_MASK" => "q1s",
+        "Q1T" | "Q1_TERNARY" => "q1t",
         _ => "q8",
     }
 }
 
+fn is_cmf_repo(repo: &str) -> bool {
+    let lower = repo.to_ascii_lowercase();
+    lower.contains("cmf") || lower.ends_with(".cmf")
+}
+
+async fn download_cmf_repo(
+    repo: String,
+    output_abs: String,
+    hf_token: Option<String>,
+    store: Arc<JobStore>,
+    id: String,
+    cancel: Arc<Notify>,
+) {
+    store.set_progress(&id, 0.0, "listing files".into());
+
+    let tree_url = format!("https://huggingface.co/api/models/{repo}/tree/main?recursive=true");
+    let client = reqwest::Client::new();
+    let mut req = client.get(&tree_url).header("User-Agent", "cortiq-gateway");
+    if let Some(t) = &hf_token {
+        req = req.bearer_auth(t);
+    }
+
+    let mut cmf_rel_path = None;
+    if let Ok(resp) = req.send().await {
+        if resp.status().is_success() {
+            if let Ok(json) = resp.json::<serde_json::Value>().await {
+                if let Some(arr) = json.as_array() {
+                    for item in arr {
+                        if let Some(path) = item.get("path").and_then(|p| p.as_str()) {
+                            if path.to_ascii_lowercase().ends_with(".cmf") {
+                                cmf_rel_path = Some(path.to_string());
+                                break;
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    let cmf_path = match cmf_rel_path {
+        Some(p) => p,
+        None => {
+            let repo_name = repo.split('/').last().unwrap_or(&repo);
+            format!("{repo_name}.cmf")
+        }
+    };
+
+    store.push_line(&id, format!("→ downloading {cmf_path} from HuggingFace..."));
+    store.set_progress(&id, 0.05, "downloading".into());
+
+    let download_url = format!("https://huggingface.co/{repo}/resolve/main/{cmf_path}");
+
+    let mut cmd = tokio::process::Command::new("curl");
+    cmd.arg("-f").arg("-L").arg("-#").arg("-o").arg(&output_abs);
+
+    if let Some(t) = &hf_token {
+        cmd.arg("-H").arg(format!("Authorization: Bearer {t}"));
+    }
+
+    cmd.arg(&download_url);
+    cmd.stderr(std::process::Stdio::piped());
+    cmd.stdout(std::process::Stdio::null());
+
+    let mut child = match cmd.spawn() {
+        Ok(c) => c,
+        Err(e) => {
+            store.push_line(&id, format!("✗ failed to start curl download: {e}"));
+            store.finish(&id, false);
+            store.drop_cancel(&id);
+            return;
+        }
+    };
+
+    let stderr = child.stderr.take();
+    let mut t_err = None;
+    if let Some(err_stream) = stderr {
+        let store_clone = store.clone();
+        let id_clone = id.clone();
+        t_err = Some(tokio::spawn(async move {
+            use tokio::io::AsyncReadExt;
+            let mut reader = err_stream;
+            let mut buf = [0u8; 256];
+            while let Ok(n) = reader.read(&mut buf).await {
+                if n == 0 {
+                    break;
+                }
+                let text = String::from_utf8_lossy(&buf[..n]);
+                for word in text.split_whitespace() {
+                    if let Some(num_str) = word.strip_suffix('%') {
+                        if let Ok(pct) = num_str.parse::<f32>() {
+                            let frac = (pct / 100.0).clamp(0.0, 1.0);
+                            store_clone.set_progress(&id_clone, frac, "downloading".into());
+                        }
+                    }
+                }
+            }
+        }));
+    }
+
+    tokio::select! {
+        status_res = child.wait() => {
+            if let Some(t) = t_err { t.abort(); }
+            match status_res {
+                Ok(status) if status.success() => {
+                    store.push_line(&id, "✓ done".into());
+                    store.finish(&id, true);
+                }
+                Ok(status) => {
+                    cleanup_output(&output_abs);
+                    store.push_line(&id, format!("✗ download failed: exit code {:?}", status.code()));
+                    store.finish(&id, false);
+                }
+                Err(e) => {
+                    cleanup_output(&output_abs);
+                    store.push_line(&id, format!("✗ download process error: {e}"));
+                    store.finish(&id, false);
+                }
+            }
+        }
+        _ = cancel.notified() => {
+            let _ = child.start_kill();
+            let _ = child.wait().await;
+            if let Some(t) = t_err { t.abort(); }
+            cleanup_output(&output_abs);
+            store.push_line(&id, "✗ cancelled by user — partial output removed".into());
+            store.set_state(&id, "cancelled");
+        }
+    }
+    store.drop_cancel(&id);
+}
+
 /// into the job log. Fails fast if the converter script is missing.
 pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Result<String, String> {
     if p.repo.trim().is_empty() {
@@ -326,13 +463,30 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
         .unwrap_or_else(|_| output.clone());
 
     let id = gen_id(&p.repo);
+    let is_cmf = is_cmf_repo(&p.repo);
+    let quant_display = if p.quant.is_empty() || p.quant == "auto" {
+        if is_cmf {
+            "READY_CMF".to_string()
+        } else {
+            "q8".to_string()
+        }
+    } else {
+        p.quant.clone()
+    };
     store.insert(Job {
         id: id.clone(),
         repo: p.repo.clone(),
-        quant: p.quant.clone(),
+        quant: quant_display.clone(),
         output: output_abs.clone(),
         state: "running".into(),
-        log: vec![format!("→ converting {} to {} ({})", p.repo, base, p.quant)],
+        log: if is_cmf {
+            vec![format!(
+                "→ downloading ready .cmf model {} ({})",
+                p.repo, quant_display
+            )]
+        } else {
+            vec![format!("→ converting {} to {} ({})", p.repo, base, p.quant)]
+        },
         started: now(),
         finished: None,
         size_bytes: None,
@@ -348,6 +502,14 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
         std::env::var(&cfg.hf_token_env).ok()
     };
 
+    if is_cmf && !use_python {
+        let ret_id = id.clone();
+        tokio::spawn(async move {
+            download_cmf_repo(p.repo, output_abs, hf_token, store, id, cancel).await;
+        });
+        return Ok(ret_id);
+    }
+
     // Program + args: `cortiq convert` by default, or the Python converter for
     // advanced options. Both stream `@PROGRESS <frac>` markers into the log.
     let (program, args, workdir): (String, Vec<String>, std::path::PathBuf) = if use_python {
@@ -530,3 +692,32 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
 
     Ok(ret_id)
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn test_map_quant_variants() {
+        assert_eq!(map_quant("Q8_2F"), "q8_2f");
+        assert_eq!(map_quant("q82f"), "q8_2f");
+        assert_eq!(map_quant("Q8_ROW"), "q8");
+        assert_eq!(map_quant("Q4_BLOCK"), "q4");
+        assert_eq!(map_quant("Q4_TILED"), "q4t");
+        assert_eq!(map_quant("q4t"), "q4t");
+        assert_eq!(map_quant("vbit"), "vbit");
+        assert_eq!(map_quant("q1"), "q1");
+        assert_eq!(map_quant("Q1P"), "q1p");
+        assert_eq!(map_quant("q1s"), "q1s");
+        assert_eq!(map_quant("Q1T"), "q1t");
+        assert_eq!(map_quant("F16"), "f16");
+    }
+
+    #[test]
+    fn test_is_cmf_repo_check() {
+        assert!(is_cmf_repo("infosave/Bonsai-8B_2bit_cmf"));
+        assert!(is_cmf_repo("infosave/Bonsai-1.7Bcmf"));
+        assert!(is_cmf_repo("user/model.cmf"));
+        assert!(!is_cmf_repo("Qwen/Qwen2.5-0.5B-Instruct"));
+    }
+}

src/state.rs

@@ -145,6 +145,14 @@ impl AppState {
         let live = Live::build(new_cfg.clone(), &self.secrets, self.router_status.clone())?;
         new_cfg.save(&self.config_path)?;
         self.live.store(Arc::new(live));
+
+        let cmf_rt = self.cmf.clone();
+        let cmf_cfg = new_cfg.cmf.clone();
+        tokio::spawn(async move {
+            cmf_rt.stop().await;
+            crate::cmf_runtime::manage(cmf_rt, cmf_cfg).await;
+        });
+
         Ok(())
     }
 

web/js/i18n/en.js

@@ -384,12 +384,21 @@ export default {
   "import.state.done": "done",
   "import.state.error": "error",
   "import.state.cancelled": "cancelled",
+  "import.featuredTitle": "Featured Ready-to-Run .cmf Models",
+  "import.readyCmfBadge": "Ready .cmf",
+  "import.directDownload": "Download",
   "import.q.q8_2f": "8-bit two-field (𝒲×θ) — recommended: best quality/size.",
   "import.q.q8_row": "8-bit per-row — simple, robust.",
   "import.q.q4": "4-bit block — smallest, lower quality.",
+  "import.q.q4_tiled": "4-bit tiled (Q4_TILED) — 1.66x faster on Metal GPU.",
   "import.q.vbit": "Variable 3–8 bit — per-expert bit budgets.",
+  "import.q.q1t": "1.58-bit ternary (Q1T) — BitNet b1.58 with sparse outliers.",
+  "import.q.q1s": "1-bit sparse (Q1S) — 1-bit base with holographic outliers.",
+  "import.q.q1p": "1-bit PTQ (Q1P) — 1-bit with error diffusion.",
+  "import.q.q1": "1-bit (Q1) — pure binary format.",
   "import.q.f16": "16-bit — no quantization.",
   "import.q.f32": "32-bit — full precision (large file).",
+
   "import.adv.title": "Advanced settings",
   "import.adv.auto": "auto",
   "import.adv.linearCore": "Linear core",

web/js/i18n/ru.js

@@ -383,12 +383,21 @@ export default {
   "import.state.done": "готово",
   "import.state.error": "ошибка",
   "import.state.cancelled": "отменено",
+  "import.featuredTitle": "Рекомендуемые готовые .cmf модели",
+  "import.readyCmfBadge": "Готовая .cmf",
+  "import.directDownload": "Скачать",
   "import.q.q8_2f": "8-бит двухполевой (𝒲×θ) — рекомендуется: лучшее качество/размер.",
   "import.q.q8_row": "8-бит построчно — просто, надёжно.",
   "import.q.q4": "4-бит блочно — компактнее, ниже качество.",
+  "import.q.q4_tiled": "4-бит тайловый (Q4_TILED) — х1.66 быстрее на Metal GPU.",
   "import.q.vbit": "Переменная 3–8 бит — per-expert бюджеты.",
+  "import.q.q1t": "1.58-бит тернарный (Q1T) — BitNet b1.58 с оутлайерами.",
+  "import.q.q1s": "1-бит спарс (Q1S) — 1-бит база с голографическими оутлайерами.",
+  "import.q.q1p": "1-бит PTQ (Q1P) — 1-бит с переносом ошибки (error diffusion).",
+  "import.q.q1": "1-бит (Q1) — чистый бинарный формат.",
   "import.q.f16": "16-бит — без квантования.",
   "import.q.f32": "32-бит — полная точность (большой файл).",
+
   "import.adv.title": "Расширенные настройки",
   "import.adv.auto": "авто",
   "import.adv.linearCore": "Линейное ядро",

web/js/views/import.js

@@ -10,11 +10,23 @@ const QUANTS = [
   ["Q8_2F", "import.q.q8_2f"],
   ["Q8_ROW", "import.q.q8_row"],
   ["Q4_BLOCK", "import.q.q4"],
+  ["Q4_TILED", "import.q.q4_tiled"],
   ["VBIT", "import.q.vbit"],
+  ["Q1T", "import.q.q1t"],
+  ["Q1S", "import.q.q1s"],
+  ["Q1P", "import.q.q1p"],
+  ["Q1", "import.q.q1"],
   ["F16", "import.q.f16"],
   ["F32", "import.q.f32"],
 ];
 
+const FEATURED_REPOS = [
+  { id: "infosave/Bonsai-1.7Bcmf", label: "Bonsai 1.7B CMF", badge: "1.7B · Q1", quant: "Q1" },
+  { id: "infosave/Bonsai-8B_2bit_cmf", label: "Bonsai 8B 2-bit CMF", badge: "8B · Q1T", quant: "Q1T" },
+  { id: "infosave/Bonsai-27Bcmf", label: "Bonsai 27B CMF", badge: "27B · Q1", quant: "Q1" },
+];
+
+
 function field(label, control, hint) {
   return h("label", { class: "field" }, h("span", {}, label), control,
     hint ? h("div", { class: "hint" }, hint) : null);
@@ -358,6 +370,46 @@ export function renderImport() {
     );
   }
 
+  function featuredCard(item) {
+    const card = h(
+      "div",
+      { class: "hf-card featured-card" },
+      h("div", { class: "row", style: "align-items:center; justify-content:space-between;" },
+        h("div", {},
+          h("div", { class: "hf-id" }, item.label),
+          h("div", { class: "hf-meta" },
+            h("span", { class: "badge" }, item.badge),
+            h("span", { class: "muted" }, item.id)
+          )
+        ),
+        h("button", { class: "btn primary sm" }, "⬇ " + t("import.directDownload"))
+      )
+    );
+    card.querySelector("button").addEventListener("click", async (e) => {
+      e.stopPropagation();
+      try {
+        await api.startImport({
+          repo: item.id,
+          quant: item.quant || "READY_CMF",
+          name: item.id.split("/").pop().toLowerCase(),
+        });
+        toast(t("import.started"), "ok");
+        refreshJobs();
+        jobsHost.scrollIntoView({ behavior: "smooth", block: "nearest" });
+      } catch (err) {
+        toast(err.message, "err");
+      }
+    });
+    return card;
+  }
+
+  const featuredHost = h(
+    "div",
+    { class: "card featured-section" },
+    h("div", { class: "card-title" }, "⚡ " + t("import.featuredTitle")),
+    h("div", { class: "hf-grid" }, ...FEATURED_REPOS.map(featuredCard))
+  );
+
   const root = h(
     "div",
     {},
@@ -365,6 +417,7 @@ export function renderImport() {
       h("h2", {}, t("nav.import")),
       h("div", { class: "muted" }, t("import.subtitle"))),
     jobsHost, // progress panel on top, above the search
+    featuredHost, // featured ready-to-run models
     h("div", { class: "card" }, searchIn, results),
     formHost
   );
@@ -372,3 +425,4 @@ export function renderImport() {
   refreshJobs(); // resume: show any running/recent conversions immediately
   return root;
 }
+