Address comment

Merge branch 'main' into leo/add-glm-5
prioritize official model cards over custom model cards
2026-02-19 07:17:30 -05:00 · 2026-02-18 16:06:30 +00:00 · 2026-02-18 13:31:04 +00:00 · 2026-02-18 13:20:05 +00:00 · 2026-02-18 13:17:39 +00:00 · 2026-02-18 12:40:31 +00:00
29 changed files with 234 additions and 591 deletions
--- a/.mlx_typings/mlx_lm/models/glm_moe_dsa.pyi
+++ b/.mlx_typings/mlx_lm/models/glm_moe_dsa.pyi
@@ -0,0 +1,46 @@
+"""Type stubs for mlx_lm.models.glm_moe_dsa"""
+
+from dataclasses import dataclass
+from typing import Any, Dict, Optional
+
+from .base import BaseModelArgs
+from .deepseek_v32 import Model as DSV32Model
+
+@dataclass
+class ModelArgs(BaseModelArgs):
+    model_type: str
+    vocab_size: int
+    hidden_size: int
+    index_head_dim: int
+    index_n_heads: int
+    index_topk: int
+    intermediate_size: int
+    moe_intermediate_size: int
+    num_hidden_layers: int
+    num_attention_heads: int
+    num_key_value_heads: int
+    n_shared_experts: Optional[int]
+    n_routed_experts: Optional[int]
+    routed_scaling_factor: float
+    kv_lora_rank: int
+    q_lora_rank: int
+    qk_rope_head_dim: int
+    v_head_dim: int
+    qk_nope_head_dim: int
+    topk_method: str
+    scoring_func: str
+    norm_topk_prob: bool
+    n_group: int
+    topk_group: int
+    num_experts_per_tok: int
+    moe_layer_freq: int
+    first_k_dense_replace: int
+    max_position_embeddings: int
+    rms_norm_eps: float
+    rope_parameters: Dict[str, Any]
+    attention_bias: bool
+    rope_scaling: Dict[str, Any] | None
+    rope_theta: float | None
+
+class Model(DSV32Model):
+    def __init__(self, config: ModelArgs) -> None: ...
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -141,12 +141,6 @@ version = "0.3.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "76a2e8124351fda1ef8aaaa3bbd7ebbcb486bbcd4225aca0aa0d84bb2db8fecb"

-[[package]]
-name = "arrayvec"
-version = "0.7.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
-
 [[package]]
 name = "asn1-rs"
 version = "0.7.1"
@@ -304,19 +298,6 @@ version = "1.8.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "55248b47b0caf0546f7988906588779981c43bb1bc9d0c44087278f80cdb44ba"

-[[package]]
-name = "bigdecimal"
-version = "0.4.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "560f42649de9fa436b73517378a147ec21f6c997a546581df4b4b31677828934"
-dependencies = [
- "autocfg",
- "libm",
- "num-bigint",
- "num-integer",
- "num-traits",
-]
-
 [[package]]
 name = "bimap"
 version = "0.6.3"
@@ -516,15 +497,6 @@ version = "0.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2f421161cb492475f1661ddc9815a745a1c894592070661180fdec3d4872e9c3"

-[[package]]
-name = "convert_case"
-version = "0.10.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "633458d4ef8c78b72454de2d54fd6ab2e60f9e02be22f3c6104cdc8a4e0fceb9"
-dependencies = [
- "unicode-segmentation",
-]
-
 [[package]]
 name = "core-foundation"
 version = "0.9.4"
@@ -746,29 +718,6 @@ dependencies = [
 "powerfmt",
 ]

-[[package]]
-name = "derive_more"
-version = "2.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "10b768e943bed7bf2cab53df09f4bc34bfd217cdb57d971e769874c9a6710618"
-dependencies = [
- "derive_more-impl",
-]
-
-[[package]]
-name = "derive_more-impl"
-version = "2.1.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6d286bfdaf75e988b4a78e013ecd79c581e06399ab53fbacd2d916c2f904f30b"
-dependencies = [
- "convert_case",
- "proc-macro2",
- "quote",
- "rustc_version",
- "syn 2.0.111",
- "unicode-xid",
-]
-
 [[package]]
 name = "digest"
 version = "0.10.7"
@@ -939,22 +888,17 @@ name = "exo_pyo3_bindings"
 version = "0.0.1"
 dependencies = [
 "delegate",
- "derive_more",
 "env_logger",
 "extend",
 "futures",
- "impl-trait-for-tuples",
 "libp2p",
 "log",
 "networking",
- "once_cell",
 "pin-project",
 "pyo3",
 "pyo3-async-runtimes",
 "pyo3-log",
 "pyo3-stub-gen",
- "thiserror 2.0.17",
- "thread_local",
 "tokio",
 "util",
 ]
@@ -1640,17 +1584,6 @@ dependencies = [
 "xmltree",
 ]

-[[package]]
-name = "impl-trait-for-tuples"
-version = "0.2.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a0eb5a3343abf848c0984fe4604b2b105da9539376e24fc0a3b0007411ae4fd9"
-dependencies = [
- "proc-macro2",
- "quote",
- "syn 2.0.111",
-]
-
 [[package]]
 name = "indexmap"
 version = "2.12.1"
@@ -1829,12 +1762,6 @@ version = "0.2.178"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "37c93d8daa9d8a012fd8ab92f088405fb202ea0b6ab73ee2482ae66af4f42091"

-[[package]]
-name = "libm"
-version = "0.2.15"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f9fbbcab51052fe104eb5e5d351cf728d30a5be1fe14d9be8a3b097481fb97de"
-
 [[package]]
 name = "libp2p"
 version = "0.56.0"
@@ -2824,16 +2751,13 @@ name = "networking"
 version = "0.0.1"
 dependencies = [
 "delegate",
- "derive_more",
 "either",
 "extend",
 "futures",
 "futures-timer",
- "impl-trait-for-tuples",
 "keccak-const",
 "libp2p",
 "log",
- "thiserror 2.0.17",
 "tokio",
 "tracing-subscriber",
 "util",
@@ -2918,17 +2842,6 @@ dependencies = [
 "num-traits",
 ]

-[[package]]
-name = "num-rational"
-version = "0.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f83d14da390562dca69fc84082e73e548e1ad308d24accdedd2720017cb37824"
-dependencies = [
- "num-bigint",
- "num-integer",
- "num-traits",
-]
-
 [[package]]
 name = "num-traits"
 version = "0.2.19"
@@ -3279,28 +3192,14 @@ version = "0.27.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ab53c047fcd1a1d2a8820fe84f05d6be69e9526be40cb03b73f86b6b03e6d87d"
 dependencies = [
- "bigdecimal",
- "either",
- "hashbrown 0.16.1",
- "indexmap",
 "indoc",
- "inventory",
 "libc",
- "lock_api",
 "memoffset",
- "num-bigint",
- "num-complex",
- "num-rational",
- "num-traits",
 "once_cell",
- "ordered-float",
- "parking_lot",
 "portable-atomic",
 "pyo3-build-config",
 "pyo3-ffi",
 "pyo3-macros",
- "rust_decimal",
- "smallvec",
 "unindent",
 ]

@@ -3741,16 +3640,6 @@ dependencies = [
 "tokio",
 ]

-[[package]]
-name = "rust_decimal"
-version = "1.39.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "35affe401787a9bd846712274d97654355d21b2a2c092a3139aabe31e9022282"
-dependencies = [
- "arrayvec",
- "num-traits",
-]
-
 [[package]]
 name = "rustc-hash"
 version = "1.1.0"
@@ -4615,24 +4504,12 @@ version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"

-[[package]]
-name = "unicode-segmentation"
-version = "1.12.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f6ccf251212114b54433ec949fd6a7841275f9ada20dddd2f29e9ceea4501493"
-
 [[package]]
 name = "unicode-width"
 version = "0.2.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"

-[[package]]
-name = "unicode-xid"
-version = "0.2.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ebc1c04c71510c7f702b52b7c350734c9ff1295c464a03335b00bb84fc54f853"
-
 [[package]]
 name = "unicode_names2"
 version = "1.3.0"
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -26,49 +26,21 @@ opt-level = 3
 networking = { path = "rust/networking" }
 util = { path = "rust/util" }

-# Proc-macro authoring tools
-syn = "2.0"
-quote = "1.0"
-proc-macro2 = "1.0"
-darling = "0.20"
-
 # Macro dependecies
 extend = "1.2"
 delegate = "0.13"
-impl-trait-for-tuples = "0.2"
-clap = "4.5"
-derive_more = { version = "2.0.1", features = ["display"] }
 pin-project = "1"

 # Utility dependencies
-itertools = "0.14"
-thiserror = "2"
-internment = "0.8"
-recursion = "0.5"
-regex = "1.11"
-once_cell = "1.21"
-thread_local = "1.1"
-bon = "3.4"
-generativity = "1.1"
-anyhow = "1.0"
 keccak-const = "0.2"

-# Functional generics/lenses frameworks
-frunk_core = "0.4"
-frunk = "0.4"
-frunk_utils = "0.2"
-frunk-enum-core = "0.3"
-
 # Async dependencies
 tokio = "1.46"
 futures = "0.3"
-futures-util = "0.3"
 futures-timer = "3.0"

 # Data structures
 either = "1.15"
-ordered-float = "5.0"
-ahash = "0.8"

 # Tracing/logging
 log = "0.4"
--- a/README.md
+++ b/README.md
@@ -72,16 +72,23 @@ There are two ways to run exo:

 ### Run from Source (macOS)

+If you have [Nix](https://nixos.org/) installed, you can skip most of the steps below and run exo directly (after accepting the Cachix cache):
+
+```bash
+nix run .#exo
+```
+
 **Prerequisites:**
+- [Xcode](https://developer.apple.com/xcode/) (provides the Metal ToolChain required for MLX compilation)
 - [brew](https://github.com/Homebrew/brew) (for simple package management on macOS)
-  
+
  ```bash
  /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
  ```
 - [uv](https://github.com/astral-sh/uv) (for Python dependency management)
 - [macmon](https://github.com/vladkens/macmon) (for hardware monitoring on Apple Silicon)
 - [node](https://github.com/nodejs/node) (for building the dashboard)
-  
+
  ```bash
  brew install uv macmon node
  ```
--- a/app/EXO/EXO/ExoProcessController.swift
+++ b/app/EXO/EXO/ExoProcessController.swift
@@ -126,11 +126,37 @@ final class ExoProcessController: ObservableObject {
            return
        }
        process.terminationHandler = nil
-        if process.isRunning {
-            process.terminate()
-        }
-        self.process = nil
        status = .stopped
+
+        guard process.isRunning else {
+            self.process = nil
+            return
+        }
+
+        let proc = process
+        self.process = nil
+
+        Task.detached {
+            proc.interrupt()
+
+            for _ in 0..<50 {
+                if !proc.isRunning { return }
+                try? await Task.sleep(nanoseconds: 100_000_000)
+            }
+
+            if proc.isRunning {
+                proc.terminate()
+            }
+
+            for _ in 0..<30 {
+                if !proc.isRunning { return }
+                try? await Task.sleep(nanoseconds: 100_000_000)
+            }
+
+            if proc.isRunning {
+                kill(proc.processIdentifier, SIGKILL)
+            }
+        }
    }

    func restart() {
--- a/flake.nix
+++ b/flake.nix
@@ -115,7 +115,7 @@
          packages = lib.optionalAttrs pkgs.stdenv.hostPlatform.isDarwin (
            let
              uvLock = builtins.fromTOML (builtins.readFile ./uv.lock);
-              mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx") uvLock.package);
+              mlxPackage = builtins.head (builtins.filter (p: p.name == "mlx" && p.source ? git) uvLock.package);
              uvLockMlxVersion = mlxPackage.version;
            in
            {
--- a/nix/mlx.nix
+++ b/nix/mlx.nix
@@ -41,16 +41,16 @@ let

  mlx = stdenv.mkDerivation rec {
    pname = "mlx";
-    version = let v = "0.30.6"; in
+    version = let v = "0.30.7.dev20260218+14841977"; in
      assert v == uvLockMlxVersion || throw "MLX version mismatch: nix/mlx.nix has ${v} but uv.lock has ${uvLockMlxVersion}. Update both the version and hash in nix/mlx.nix.";
      v;
    pyproject = true;

    src = fetchFromGitHub {
-      owner = "ml-explore";
-      repo = "mlx";
-      tag = "v${version}";
-      hash = "sha256-avD5EGhwgmPdXLAyQSqTO6AXk/W3ziH+f6AetjK3Sdo=";
+      owner = "rltakashige";
+      repo = "mlx-jaccl-fix-small-recv";
+      rev = "1484197707f35186ad3bd614357c7c47fdf86ebc";
+      hash = "sha256-FupCMoK/SF/ldfKuvMSAKECcOP8c+ANgkQlPZttDsLk=";
    };

    patches = [
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -17,9 +17,9 @@ dependencies = [
    "loguru>=0.7.3",
    "exo_pyo3_bindings", # rust bindings
    "anyio==4.11.0",
-    "mlx==0.30.6; sys_platform == 'darwin'",
+    "mlx; sys_platform == 'darwin'",
    "mlx[cpu]==0.30.6; sys_platform == 'linux'",
-    "mlx-lm==0.30.6",
+    "mlx-lm==0.30.7",
    "tiktoken>=0.12.0", # required for kimi k2 tokenizer
    "hypercorn>=0.18.0",
    "openai-harmony>=0.0.8",
@@ -64,6 +64,7 @@ members = [

 [tool.uv.sources]
 exo_pyo3_bindings = { workspace = true }
+mlx = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git", branch = "address-rdma-gpu-locks", marker = "sys_platform == 'darwin'" }
 #mlx-lm = { git = "https://github.com/davidmcc73/mlx-lm", branch = "stable" }
 # Uncomment to use local mlx/mlx-lm development versions:
 # mlx = { path = "/Users/Shared/mlx", editable=true }
--- a/python/parts.nix
+++ b/python/parts.nix
@@ -58,6 +58,21 @@
        lib.optionalAttrs pkgs.stdenv.hostPlatform.isLinux (
          (lib.mapAttrs (_: ignoreMissing) nvidiaPackages) // {
            mlx = ignoreMissing prev.mlx;
+            mlx-cuda-13 = prev.mlx-cuda-13.overrideAttrs (old: {
+              buildInputs = (old.buildInputs or [ ]) ++ [
+                final.nvidia-cublas
+                final.nvidia-cuda-nvrtc
+                final.nvidia-cudnn-cu13
+                final.nvidia-nccl-cu13
+              ];
+              preFixup = ''
+                addAutoPatchelfSearchPath ${final.nvidia-cublas}
+                addAutoPatchelfSearchPath ${final.nvidia-cuda-nvrtc}
+                addAutoPatchelfSearchPath ${final.nvidia-cudnn-cu13}
+                addAutoPatchelfSearchPath ${final.nvidia-nccl-cu13}
+              '';
+              autoPatchelfIgnoreMissingDeps = [ "libcuda.so.1" ];
+            });
            torch = ignoreMissing prev.torch;
            triton = ignoreMissing prev.triton;
          }
@@ -74,14 +89,25 @@
          linuxOverlay
        ]
      );
-      exoVenv = pythonSet.mkVirtualEnv "exo-env" workspace.deps.default;
+      # mlx-cpu and mlx-cuda-13 both ship mlx/ site-packages files; keep first.
+      # mlx-cpu/mlx-cuda-13 and nvidia-cudnn-cu12/cu13 ship overlapping files.
+      venvCollisionPaths = lib.optionals pkgs.stdenv.hostPlatform.isLinux [
+        "lib/python3.13/site-packages/mlx*"
+        "lib/python3.13/site-packages/nvidia*"
+      ];
+
+      exoVenv = (pythonSet.mkVirtualEnv "exo-env" workspace.deps.default).overrideAttrs {
+        venvIgnoreCollisions = venvCollisionPaths;
+      };

      # Virtual environment with dev dependencies for testing
-      testVenv = pythonSet.mkVirtualEnv "exo-test-env" (
+      testVenv = (pythonSet.mkVirtualEnv "exo-test-env" (
        workspace.deps.default // {
          exo = [ "dev" ]; # Include pytest, pytest-asyncio, pytest-env
        }
-      );
+      )).overrideAttrs {
+        venvIgnoreCollisions = venvCollisionPaths;
+      };

      mkPythonScript = name: path: pkgs.writeShellApplication {
        inherit name;
--- a/resources/inference_model_cards/mlx-community--GLM-5-8bit.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-5-8bit.toml
@@ -0,0 +1,12 @@
+model_id = "mlx-community/GLM-5-8bit-MXFP8"
+n_layers = 78
+hidden_size = 6144
+supports_tensor = true
+tasks = ["TextGeneration"]
+family = "glm"
+quantization = "8bit"
+base_model = "GLM-5"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 790517400864
--- a/resources/inference_model_cards/mlx-community--GLM-5-MXFP4-Q8.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-5-MXFP4-Q8.toml
@@ -0,0 +1,12 @@
+model_id = "mlx-community/GLM-5-MXFP4-Q8"
+n_layers = 78
+hidden_size = 6144
+supports_tensor = true
+tasks = ["TextGeneration"]
+family = "glm"
+quantization = "MXFP4-Q8"
+base_model = "GLM-5"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 405478939008
--- a/resources/inference_model_cards/mlx-community--GLM-5-bf16.toml
+++ b/resources/inference_model_cards/mlx-community--GLM-5-bf16.toml
@@ -0,0 +1,12 @@
+model_id = "mlx-community/GLM-5"
+n_layers = 78
+hidden_size = 6144
+supports_tensor = true
+tasks = ["TextGeneration"]
+family = "glm"
+quantization = "bf16"
+base_model = "GLM-5"
+capabilities = ["text", "thinking"]
+
+[storage_size]
+in_bytes = 1487822475264
--- a/rust/exo_pyo3_bindings/Cargo.toml
+++ b/rust/exo_pyo3_bindings/Cargo.toml
@@ -25,17 +25,17 @@ workspace = true
 networking = { workspace = true }

 # interop
-pyo3 = { version = "0.27.1", features = [
-    # "abi3-py311", # tells pyo3 (and maturin) to build using the stable ABI with minimum Python version 3.11
+pyo3 = { version = "0.27.2", features = [
+    # "abi3-py313", # tells pyo3 (and maturin) to build using the stable ABI with minimum Python version 3.13
    "nightly", # enables better-supported GIL integration
    "experimental-async", # async support in #[pyfunction] & #[pymethods]
    #"experimental-inspect", # inspection of generated binary => easier to automate type-hint generation
    #"py-clone", # adding Clone-ing of `Py<T>` without GIL (may cause panics - remove if panics happen)
-    "multiple-pymethods", # allows multiple #[pymethods] sections per class
+    # "multiple-pymethods", # allows multiple #[pymethods] sections per class

    # integrations with other libraries
-    "arc_lock", "bigdecimal", "either", "hashbrown", "indexmap", "num-bigint", "num-complex", "num-rational",
-    "ordered-float", "rust_decimal", "smallvec",
+    # "arc_lock", "bigdecimal", "either", "hashbrown", "indexmap", "num-bigint", "num-complex", "num-rational",
+    # "ordered-float", "rust_decimal", "smallvec",
    # "anyhow", "chrono", "chrono-local", "chrono-tz", "eyre", "jiff-02", "lock_api", "parking-lot", "time",  "serde",
 ] }
 pyo3-stub-gen = { version = "0.17.2" }
@@ -45,8 +45,6 @@ pyo3-log = "0.13.2"
 # macro dependencies
 extend = { workspace = true }
 delegate = { workspace = true }
-impl-trait-for-tuples = { workspace = true }
-derive_more = { workspace = true }
 pin-project = { workspace = true }

 # async runtime
@@ -54,24 +52,11 @@ tokio = { workspace = true, features = ["full", "tracing"] }
 futures = { workspace = true }

 # utility dependencies
-once_cell = "1.21.3"
-thread_local = "1.1.9"
 util = { workspace = true }
-thiserror = { workspace = true }
-#internment = { workspace = true }
-#recursion = { workspace = true }
-#generativity = { workspace = true }
-#itertools = { workspace = true }
-

 # Tracing
-#tracing = "0.1"
-#tracing-subscriber = "0.3"
-#console-subscriber = "0.1.5"
-#tracing-log = "0.2.0"
 log = { workspace = true }
 env_logger = "0.11"

-
 # Networking
 libp2p = { workspace = true, features = ["full"] }
--- a/rust/exo_pyo3_bindings/src/allow_threading.rs
+++ b/rust/exo_pyo3_bindings/src/allow_threading.rs
@@ -6,7 +6,7 @@ use pyo3::marker::Ungil;
 use pyo3::prelude::*;
 use std::{
    future::Future,
-    pin::{Pin, pin},
+    pin::Pin,
    task::{Context, Poll},
 };

@@ -33,8 +33,6 @@ where

    fn poll(self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Self::Output> {
        let waker = cx.waker();
-        Python::with_gil(|py| {
-            py.allow_threads(|| self.project().0.poll(&mut Context::from_waker(waker)))
-        })
+        Python::attach(|py| py.detach(|| self.project().0.poll(&mut Context::from_waker(waker))))
    }
 }
--- a/rust/exo_pyo3_bindings/src/examples/mod.rs
+++ b/rust/exo_pyo3_bindings/src/examples/mod.rs
@@ -1,240 +0,0 @@
-//! This module exists to hold examples of some pyo3 patterns that may be too complex to
-//! re-create from scratch, but too inhomogenous to create an abstraction/wrapper around.
-//!
-//! Pattern examples include:
-//!  - Async task handles: with GC-integrated cleanup
-//!  - Sync/async callbacks from python: with propper eventloop handling
-//!
-//! Mutability pattern: https://pyo3.rs/v0.26.0/async-await.html#send--static-constraint
-//!  - Store mutable fields in tokio's `Mutex<T>`
-//!  - For async code: take `&self` and `.lock().await`
-//!  - For sync code: take `&mut self` and `.get_mut()`
-
-use crate::ext::{PyResultExt as _, ResultExt as _, TokioRuntimeExt as _};
-use futures::FutureExt as _;
-use futures::future::BoxFuture;
-use pyo3::exceptions::PyRuntimeError;
-use pyo3::prelude::{PyModule, PyModuleMethods as _};
-use pyo3::{
-    Bound, Py, PyAny, PyErr, PyResult, PyTraverseError, PyVisit, Python, pyclass, pymethods,
-};
-use std::time::Duration;
-use tokio::sync::mpsc;
-use tokio::sync::mpsc::error::TryRecvError;
-
-fn needs_tokio_runtime() {
-    tokio::runtime::Handle::current();
-}
-
-type SyncCallback = Box<dyn Fn() + Send + Sync>;
-type AsyncCallback = Box<dyn Fn() -> BoxFuture<'static, ()> + Send + Sync>;
-
-enum AsyncTaskMessage {
-    SyncCallback(SyncCallback),
-    AsyncCallback(AsyncCallback),
-}
-
-async fn async_task(
-    sender: mpsc::UnboundedSender<()>,
-    mut receiver: mpsc::UnboundedReceiver<AsyncTaskMessage>,
-) {
-    log::info!("RUST: async task started");
-
-    // task state
-    let mut interval = tokio::time::interval(Duration::from_secs(1));
-
-    let mut sync_cbs: Vec<SyncCallback> = vec![];
-    let mut async_cbs: Vec<AsyncCallback> = vec![];
-
-    loop {
-        tokio::select! {
-            // handle incoming messages from task-handle
-            message = receiver.recv() => {
-                // handle closed channel by exiting
-                let Some(message) = message else {
-                    log::info!("RUST: channel closed");
-                    break;
-                };
-
-                // dispatch incoming event
-                match message {
-                    AsyncTaskMessage::SyncCallback(cb) => {
-                        sync_cbs.push(cb);
-                    }
-                    AsyncTaskMessage::AsyncCallback(cb) => {
-                        async_cbs.push(cb);
-                    }
-                }
-            }
-
-            // handle all other events
-            _ = interval.tick() => {
-                log::info!("RUST: async task tick");
-
-                // call back all sync callbacks
-                for cb in &sync_cbs {
-                    cb();
-                }
-
-                // call back all async callbacks
-                for cb in &async_cbs {
-                    cb().await;
-                }
-
-                // send event on unbounded channel
-                sender.send(()).expect("handle receiver cannot be closed/dropped");
-            }
-        }
-    }
-
-    log::info!("RUST: async task stopped");
-}
-
-// #[gen_stub_pyclass]
-#[pyclass(name = "AsyncTaskHandle")]
-#[derive(Debug)]
-struct PyAsyncTaskHandle {
-    sender: Option<mpsc::UnboundedSender<AsyncTaskMessage>>,
-    receiver: mpsc::UnboundedReceiver<()>,
-}
-
-#[allow(clippy::expect_used)]
-impl PyAsyncTaskHandle {
-    const fn sender(&self) -> &mpsc::UnboundedSender<AsyncTaskMessage> {
-        self.sender
-            .as_ref()
-            .expect("The sender should only be None after de-initialization.")
-    }
-
-    const fn sender_mut(&mut self) -> &mpsc::UnboundedSender<AsyncTaskMessage> {
-        self.sender
-            .as_mut()
-            .expect("The sender should only be None after de-initialization.")
-    }
-
-    const fn new(
-        sender: mpsc::UnboundedSender<AsyncTaskMessage>,
-        receiver: mpsc::UnboundedReceiver<()>,
-    ) -> Self {
-        Self {
-            sender: Some(sender),
-            receiver,
-        }
-    }
-}
-
-// #[gen_stub_pymethods]
-#[pymethods]
-impl PyAsyncTaskHandle {
-    #[new]
-    fn py_new(py: Python<'_>) -> PyResult<Self> {
-        use pyo3_async_runtimes::tokio::get_runtime;
-
-        // create communication channel TOWARDS our task
-        let (h_sender, t_receiver) = mpsc::unbounded_channel::<AsyncTaskMessage>();
-
-        // create communication channel FROM our task
-        let (t_sender, h_receiver) = mpsc::unbounded_channel::<()>();
-
-        // perform necessary setup within tokio context - or it crashes
-        let () = get_runtime().block_on(async { needs_tokio_runtime() });
-
-        // spawn tokio task with this thread's task-locals - without this, async callbacks on the new threads will not work!!
-        _ = get_runtime().spawn_with_scope(py, async move {
-            async_task(t_sender, t_receiver).await;
-        });
-        Ok(Self::new(h_sender, h_receiver))
-    }
-
-    /// NOTE: exceptions in callbacks are silently ignored until end of execution
-    fn add_sync_callback(
-        &self,
-        // #[gen_stub(override_type(
-        //     type_repr="collections.abc.Callable[[], None]",
-        //     imports=("collections.abc")
-        // ))]
-        callback: Py<PyAny>,
-    ) -> PyResult<()> {
-        // blocking call to async method -> can do non-blocking if needed
-        self.sender()
-            .send(AsyncTaskMessage::SyncCallback(Box::new(move || {
-                _ = Python::with_gil(|py| callback.call0(py).write_unraisable_with(py));
-            })))
-            .pyerr()?;
-        Ok(())
-    }
-
-    /// NOTE: exceptions in callbacks are silently ignored until end of execution
-    fn add_async_callback(
-        &self,
-        // #[gen_stub(override_type(
-        //     type_repr="collections.abc.Callable[[], collections.abc.Awaitable[None]]",
-        //     imports=("collections.abc")
-        // ))]
-        callback: Py<PyAny>,
-    ) -> PyResult<()> {
-        // blocking call to async method -> can do non-blocking if needed
-        self.sender()
-            .send(AsyncTaskMessage::AsyncCallback(Box::new(move || {
-                let c = Python::with_gil(|py| callback.clone_ref(py));
-                async move {
-                    if let Some(f) = Python::with_gil(|py| {
-                        let coroutine = c.call0(py).write_unraisable_with(py)?;
-                        pyo3_async_runtimes::tokio::into_future(coroutine.into_bound(py))
-                            .write_unraisable_with(py)
-                    }) {
-                        _ = f.await.write_unraisable();
-                    }
-                }
-                .boxed()
-            })))
-            .pyerr()?;
-        Ok(())
-    }
-
-    async fn receive_unit(&mut self) -> PyResult<()> {
-        self.receiver
-            .recv()
-            .await
-            .ok_or(PyErr::new::<PyRuntimeError, _>(
-                "cannot receive unit on closed channel",
-            ))
-    }
-
-    fn drain_units(&mut self) -> PyResult<i32> {
-        let mut cnt = 0;
-        loop {
-            match self.receiver.try_recv() {
-                Err(TryRecvError::Disconnected) => {
-                    return Err(PyErr::new::<PyRuntimeError, _>(
-                        "cannot receive unit on closed channel",
-                    ));
-                }
-                Err(TryRecvError::Empty) => return Ok(cnt),
-                Ok(()) => {
-                    cnt += 1;
-                    continue;
-                }
-            }
-        }
-    }
-
-    // #[gen_stub(skip)]
-    const fn __traverse__(&self, _visit: PyVisit<'_>) -> Result<(), PyTraverseError> {
-        Ok(()) // This is needed purely so `__clear__` can work
-    }
-
-    // #[gen_stub(skip)]
-    fn __clear__(&mut self) {
-        // TODO: may or may not need to await a "kill-signal" oneshot channel message,
-        //       to ensure that the networking task is done BEFORE exiting the clear function...
-        //       but this may require GIL?? and it may not be safe to call GIL here??
-        self.sender = None; // Using Option<T> as a trick to force `sender` channel to be dropped
-    }
-}
-
-pub fn examples_submodule(m: &Bound<'_, PyModule>) -> PyResult<()> {
-    m.add_class::<PyAsyncTaskHandle>()?;
-
-    Ok(())
-}
--- a/rust/exo_pyo3_bindings/src/lib.rs
+++ b/rust/exo_pyo3_bindings/src/lib.rs
@@ -17,7 +17,6 @@

 extern crate core;
 mod allow_threading;
-mod examples;
 pub(crate) mod networking;
 pub(crate) mod pylibp2p;

@@ -25,7 +24,6 @@ use crate::networking::networking_submodule;
 use crate::pylibp2p::ident::ident_submodule;
 use crate::pylibp2p::multiaddr::multiaddr_submodule;
 use pyo3::prelude::PyModule;
-use pyo3::prelude::*;
 use pyo3::{Bound, PyResult, pyclass, pymodule};
 use pyo3_stub_gen::define_stub_info_gatherer;

@@ -36,14 +34,10 @@ pub(crate) mod r#const {

 /// Namespace for all the type/trait aliases used by this crate.
 pub(crate) mod alias {
-    use std::error::Error;
    use std::marker::Tuple;

    pub trait SendFn<Args: Tuple + Send + 'static, Output> =
        Fn<Args, Output = Output> + Send + 'static;
-
-    pub type AnyError = Box<dyn Error + Send + Sync + 'static>;
-    pub type AnyResult<T> = Result<T, AnyError>;
 }

 /// Namespace for crate-wide extension traits/methods
@@ -51,7 +45,6 @@ pub(crate) mod ext {
    use crate::allow_threading::AllowThreads;
    use extend::ext;
    use pyo3::exceptions::{PyConnectionError, PyRuntimeError};
-    use pyo3::marker::Ungil;
    use pyo3::types::PyBytes;
    use pyo3::{Py, PyErr, PyResult, Python};
    use tokio::runtime::Runtime;
@@ -62,7 +55,7 @@ pub(crate) mod ext {
    #[ext(pub, name = ByteArrayExt)]
    impl [u8] {
        fn pybytes(&self) -> Py<PyBytes> {
-            Python::with_gil(|py| PyBytes::new(py, self).unbind())
+            Python::attach(|py| PyBytes::new(py, self).unbind())
        }
    }

@@ -98,7 +91,7 @@ pub(crate) mod ext {
    #[ext(pub, name = PyResultExt)]
    impl<T> PyResult<T> {
        fn write_unraisable(self) -> Option<T> {
-            Python::with_gil(|py| self.write_unraisable_with(py))
+            Python::attach(|py| self.write_unraisable_with(py))
        }

        fn write_unraisable_with(self, py: Python<'_>) -> Option<T> {
@@ -175,24 +168,6 @@ pub(crate) mod ext {
    }
 }

-pub(crate) mod private {
-    use std::marker::Sized;
-
-    /// Sealed traits support
-    pub trait Sealed {}
-    impl<T: ?Sized> Sealed for T {}
-}
-
-/// A wrapper around [`Py`] that implements [`Clone`] using [`Python::with_gil`].
-#[repr(transparent)]
-pub(crate) struct ClonePy<T>(pub Py<T>);
-
-impl<T> Clone for ClonePy<T> {
-    fn clone(&self) -> Self {
-        Python::with_gil(|py| Self(self.0.clone_ref(py)))
-    }
-}
-
 /// A Python module implemented in Rust. The name of this function must match
 /// the `lib.name` setting in the `Cargo.toml`, else Python will not be able to
 /// import the module.
--- a/rust/exo_pyo3_bindings/src/networking.rs
+++ b/rust/exo_pyo3_bindings/src/networking.rs
@@ -11,9 +11,9 @@ use crate::ext::{ResultExt as _, TokioMpscReceiverExt as _, TokioMpscSenderExt a
 use crate::pyclass;
 use crate::pylibp2p::ident::{PyKeypair, PyPeerId};
 use libp2p::futures::StreamExt as _;
+use libp2p::gossipsub;
 use libp2p::gossipsub::{IdentTopic, Message, MessageId, PublishError};
 use libp2p::swarm::SwarmEvent;
-use libp2p::{gossipsub, mdns};
 use networking::discovery;
 use networking::swarm::create_swarm;
 use pyo3::prelude::{PyModule, PyModuleMethods as _};
@@ -25,7 +25,7 @@ use tokio::sync::{Mutex, mpsc, oneshot};

 mod exception {
    use pyo3::types::PyTuple;
-    use pyo3::{PyErrArguments, exceptions::PyException, prelude::*};
+    use pyo3::{exceptions::PyException, prelude::*};
    use pyo3_stub_gen::derive::*;

    #[gen_stub_pyclass]
@@ -155,7 +155,6 @@ async fn networking_task(
 ) {
    use SwarmEvent::*;
    use ToTask::*;
-    use mdns::Event::*;
    use networking::swarm::BehaviourEvent::*;

    log::info!("RUST: networking task started");
@@ -485,7 +484,7 @@ impl PyNetworkingHandle {
        let (tx, rx) = oneshot::channel();

        // send off request to subscribe
-        let data = Python::with_gil(|py| Vec::from(data.as_bytes(py)));
+        let data = Python::attach(|py| Vec::from(data.as_bytes(py)));
        self.to_task_tx()
            .send_py(ToTask::GossipsubPublish {
                topic,
--- a/rust/networking/Cargo.toml
+++ b/rust/networking/Cargo.toml
@@ -19,8 +19,6 @@ either = { workspace = true }
 # macro dependencies
 extend = { workspace = true }
 delegate = { workspace = true }
-impl-trait-for-tuples = { workspace = true }
-derive_more = { workspace = true }

 # async
 tokio = { workspace = true, features = ["full"] }
@@ -29,11 +27,6 @@ futures-timer = { workspace = true }

 # utility dependencies
 util = { workspace = true }
-thiserror = { workspace = true }
-#internment = { workspace = true }
-#recursion = { workspace = true }
-#generativity = { workspace = true }
-#itertools = { workspace = true }
 tracing-subscriber = { version = "0.3.19", features = ["default", "env-filter"] }
 keccak-const = { workspace = true }

@@ -41,4 +34,4 @@ keccak-const = { workspace = true }
 log = { workspace = true }

 # networking
-libp2p = { workspace = true, features = ["full"] }
+libp2p = { workspace = true, features = ["full"] }
--- a/rust/networking/examples/chatroom_manual.rs
+++ b/rust/networking/examples/chatroom_manual.rs
@@ -24,8 +24,8 @@ use libp2p::{
    swarm::{NetworkBehaviour, SwarmEvent},
    tcp, yamux,
 };
+use std::error::Error;
 use std::time::Duration;
-use std::{error::Error, hash::Hash};
 use tokio::{io, io::AsyncBufReadExt, select};
 use tracing_subscriber::EnvFilter;

--- a/rust/networking/src/discovery.rs
+++ b/rust/networking/src/discovery.rs
@@ -1,5 +1,4 @@
 use crate::ext::MultiaddrExt;
-use crate::keep_alive;
 use delegate::delegate;
 use either::Either;
 use futures::FutureExt;
--- a/rust/networking/src/keep_alive.rs
+++ b/rust/networking/src/keep_alive.rs
@@ -1,44 +0,0 @@
-use delegate::delegate;
-use libp2p::swarm::handler::ConnectionEvent;
-use libp2p::swarm::{ConnectionHandlerEvent, SubstreamProtocol, dummy, handler};
-use std::task::{Context, Poll};
-
-/// An implementation of [`ConnectionHandler`] that doesn't handle any protocols, but it keeps
-/// the connection alive.
-#[derive(Clone)]
-#[repr(transparent)]
-pub struct ConnectionHandler(dummy::ConnectionHandler);
-
-impl ConnectionHandler {
-    pub fn new() -> Self {
-        ConnectionHandler(dummy::ConnectionHandler)
-    }
-}
-
-impl handler::ConnectionHandler for ConnectionHandler {
-    // delegate types and implementation mostly to dummy handler
-    type FromBehaviour = <dummy::ConnectionHandler as handler::ConnectionHandler>::FromBehaviour;
-    type ToBehaviour = <dummy::ConnectionHandler as handler::ConnectionHandler>::ToBehaviour;
-    type InboundProtocol =
-        <dummy::ConnectionHandler as handler::ConnectionHandler>::InboundProtocol;
-    type OutboundProtocol =
-        <dummy::ConnectionHandler as handler::ConnectionHandler>::OutboundProtocol;
-    type InboundOpenInfo =
-        <dummy::ConnectionHandler as handler::ConnectionHandler>::InboundOpenInfo;
-    type OutboundOpenInfo =
-        <dummy::ConnectionHandler as handler::ConnectionHandler>::OutboundOpenInfo;
-
-    delegate! {
-        to self.0 {
-            fn listen_protocol(&self) -> SubstreamProtocol<Self::InboundProtocol, Self::InboundOpenInfo>;
-            fn poll(&mut self, cx: &mut Context<'_>) -> Poll<ConnectionHandlerEvent<Self::OutboundProtocol, Self::OutboundOpenInfo, Self::ToBehaviour>>;
-            fn on_behaviour_event(&mut self, event: Self::FromBehaviour);
-            fn on_connection_event(&mut self, event: ConnectionEvent<Self::InboundProtocol, Self::OutboundProtocol, Self::InboundOpenInfo, Self::OutboundOpenInfo>);
-        }
-    }
-
-    // specifically override this to force connection to stay alive
-    fn connection_keep_alive(&self) -> bool {
-        true
-    }
-}
--- a/rust/networking/src/lib.rs
+++ b/rust/networking/src/lib.rs
@@ -3,19 +3,7 @@
 //! this is here as a placeholder documentation
 //!
 //!
-
-// enable Rust-unstable features for convenience
-#![feature(trait_alias)]
-// #![feature(stmt_expr_attributes)]
-// #![feature(unboxed_closures)]
-// #![feature(assert_matches)]
-// #![feature(async_fn_in_dyn_trait)]
-// #![feature(async_for_loop)]
-// #![feature(auto_traits)]
-// #![feature(negative_impls)]
-
 pub mod discovery;
-pub mod keep_alive;
 pub mod swarm;

 /// Namespace for all the type/trait aliases used by this crate.
@@ -54,11 +42,3 @@ pub(crate) mod ext {
        }
    }
 }
-
-pub(crate) mod private {
-    #![allow(dead_code)]
-
-    /// Sealed traits support
-    pub trait Sealed {}
-    impl<T: ?Sized> Sealed for T {}
-}
--- a/src/exo/main.py
+++ b/src/exo/main.py
@@ -136,6 +136,8 @@ class Node:

    async def run(self):
        async with self._tg as tg:
+            signal.signal(signal.SIGINT, lambda _, __: self.shutdown())
+            signal.signal(signal.SIGTERM, lambda _, __: self.shutdown())
            tg.start_soon(self.router.run)
            tg.start_soon(self.election.run)
            if self.download_coordinator:
@@ -147,8 +149,6 @@ class Node:
            if self.api:
                tg.start_soon(self.api.run)
            tg.start_soon(self._elect_loop)
-            signal.signal(signal.SIGINT, lambda _, __: self.shutdown())
-            signal.signal(signal.SIGTERM, lambda _, __: self.shutdown())

    def shutdown(self):
        # if this is our second call to shutdown, just sys.exit
--- a/src/exo/shared/models/model_cards.py
+++ b/src/exo/shared/models/model_cards.py
@@ -44,7 +44,8 @@ async def _refresh_card_cache():
        async for toml_file in path.rglob("*.toml"):
            try:
                card = await ModelCard.load_from_path(toml_file)
-                _card_cache[card.model_id] = card
+                if card.model_id not in _card_cache:
+                    _card_cache[card.model_id] = card
            except (ValidationError, TOMLKitError):
                pass

@@ -182,6 +183,7 @@ class ConfigData(BaseModel):
    def supports_tensor(self) -> bool:
        return self.architectures in [
            ["Glm4MoeLiteForCausalLM"],
+            ["GlmMoeDsaForCausalLM"],
            ["DeepseekV32ForCausalLM"],
            ["DeepseekV3ForCausalLM"],
            ["Qwen3NextForCausalLM"],
--- a/src/exo/worker/engines/mlx/auto_parallel.py
+++ b/src/exo/worker/engines/mlx/auto_parallel.py
@@ -163,11 +163,14 @@ class PipelineLastLayer(CustomMlxLayer):
                output, (self.r + 1) % self.s, group=self.group
            )
            if cache is not None:
-                cache.keys = mx.depends(cache.keys, output)  # type: ignore[reportUnknownMemberType]
+                # CacheList (used by MLA models like DeepSeekV32, GLM MoE DSA)
+                # doesn't have .keys directly; access via first sub-cache.
+                _cache = cache[0] if hasattr(cache, "caches") else cache  # type: ignore
+                _cache.keys = mx.depends(_cache.keys, output)  # type: ignore
            if self.is_prefill:
                mx.eval(output)
                if cache is not None:
-                    mx.eval(cache.keys)  # type: ignore
+                    mx.eval(_cache.keys)  # type: ignore

        if not self.is_prefill:
            output = mx.distributed.all_gather(output, group=self.group)[
@@ -307,7 +310,9 @@ def patch_pipeline_model[T](model: T, group: mx.distributed.Group) -> T:

        # Add dependency to last cache entry to ensure distributed ops are evaluated
        if cache is not None:
-            cache[-1].state = mx.depends(cache[-1].state, logits)  # type: ignore
+            last = cache[-1]  # type: ignore
+            dep_cache = last[0] if hasattr(last, "caches") else last  # type: ignore
+            dep_cache.keys = mx.depends(dep_cache.keys, logits)  # type: ignore

        return logits

@@ -333,7 +338,9 @@ def patch_tensor_model[T](model: T) -> T:

        # Add dependency to last cache entry to ensure distributed ops are evaluated
        if cache is not None and len(cache) > 0:  # pyright: ignore[reportAny]
-            cache[-1].state = mx.depends(cache[-1].state, logits)  # pyright: ignore[reportAny,reportUnknownMemberType]
+            last = cache[-1]  # pyright: ignore[reportAny]
+            dep_cache = last[0] if hasattr(last, "caches") else last  # pyright: ignore[reportAny]
+            dep_cache.keys = mx.depends(dep_cache.keys, logits)  # pyright: ignore[reportAny,reportUnknownMemberType]

        return logits

@@ -547,10 +554,12 @@ class DeepSeekShardingStrategy(TensorParallelShardingStrategy):
        on_timeout: TimeoutCallback | None,
    ) -> nn.Module:
        model = cast(DeepseekV3Model, model)
+
        for layer in model.layers:
            eval_with_timeout(
                layer.parameters(), timeout_seconds / len(model.layers), on_timeout
            )
+
            # Shard the self attention
            if layer.self_attn.q_lora_rank is None:
                layer.self_attn.q_proj = self.all_to_sharded_linear(
@@ -581,12 +590,18 @@ class DeepSeekShardingStrategy(TensorParallelShardingStrategy):
                layer.mlp.down_proj = self.sharded_to_all_linear(layer.mlp.down_proj)
                layer.mlp.up_proj = self.all_to_sharded_linear(layer.mlp.up_proj)

-            # Shard the MoE. Shard in place since the MoE should be responsible
-            # for aggregating the results.
+            # Shard the MoE.
            else:
-                self.all_to_sharded_linear_in_place(layer.mlp.shared_experts.gate_proj)
-                self.sharded_to_all_linear_in_place(layer.mlp.shared_experts.down_proj)
-                self.all_to_sharded_linear_in_place(layer.mlp.shared_experts.up_proj)
+                if getattr(layer.mlp, "shared_experts", None) is not None:
+                    self.all_to_sharded_linear_in_place(
+                        layer.mlp.shared_experts.gate_proj
+                    )
+                    self.sharded_to_all_linear_in_place(
+                        layer.mlp.shared_experts.down_proj
+                    )
+                    self.all_to_sharded_linear_in_place(
+                        layer.mlp.shared_experts.up_proj
+                    )
                self.all_to_sharded_linear_in_place(layer.mlp.switch_mlp.gate_proj)
                self.sharded_to_all_linear_in_place(layer.mlp.switch_mlp.down_proj)
                self.all_to_sharded_linear_in_place(layer.mlp.switch_mlp.up_proj)
@@ -779,8 +794,7 @@ class MiniMaxShardingStrategy(TensorParallelShardingStrategy):

            layer.self_attn = WrappedMiniMaxAttention(layer.self_attn, self.group)  # pyright: ignore[reportAttributeAccessIssue,reportArgumentType]

-            # Shard the MoE. Shard in place since the MoE should be responsible
-            # for aggregating the results.
+            # Shard the MoE.
            self.all_to_sharded_linear_in_place(
                layer.block_sparse_moe.switch_mlp.gate_proj
            )
@@ -893,8 +907,7 @@ class QwenShardingStrategy(TensorParallelShardingStrategy):
                    layer.self_attn.num_attention_heads //= self.N
                    layer.self_attn.num_key_value_heads //= self.N

-            # Shard the MoE. Shard in place since the MoE should be responsible
-            # for aggregating the results.
+            # Shard the MoE.
            if isinstance(layer.mlp, (Qwen3MoeSparseMoeBlock, Qwen3NextSparseMoeBlock)):
                self.all_to_sharded_linear_in_place(layer.mlp.switch_mlp.gate_proj)
                self.sharded_to_all_linear_in_place(layer.mlp.switch_mlp.down_proj)
--- a/src/exo/worker/engines/mlx/generator/generate.py
+++ b/src/exo/worker/engines/mlx/generator/generate.py
@@ -57,6 +57,7 @@ def prefill(
    sampler: Callable[[mx.array], mx.array],
    prompt_tokens: mx.array,
    cache: KVCacheType,
+    group: mx.distributed.Group | None,
 ) -> tuple[float, int, list[CacheSnapshot]]:
    """Prefill the KV cache with prompt tokens.

@@ -86,6 +87,9 @@ def prefill(

    set_pipeline_prefill(model, is_prefill=True)

+    mx_barrier(group)
+    logger.info("Starting prefill")
+
    # Use max_tokens=1 because max_tokens=0 does not work.
    # We just throw away the generated token - we only care about filling the cache
    for _ in stream_generate(
@@ -305,16 +309,9 @@ def mlx_generate(
    )
    max_stop_len = max((len(s) for s in stop_sequences), default=0)

-    mx_barrier(group)
-    logger.info("Starting prefill")
-
    # Prefill cache with all tokens except the last one
    prefill_tps, prefill_tokens, ssm_snapshots_list = prefill(
-        model,
-        tokenizer,
-        sampler,
-        prompt_tokens[:-1],
-        caches,
+        model, tokenizer, sampler, prompt_tokens[:-1], caches, group
    )
    cache_snapshots: list[CacheSnapshot] | None = ssm_snapshots_list or None

@@ -331,6 +328,7 @@ def mlx_generate(
    think_start = tokenizer.think_start
    think_end = tokenizer.think_end

+    logger.info("Starting decode")
    mx_barrier(group)

    for completion_tokens, out in enumerate(
--- a/src/exo/worker/engines/mlx/utils_mlx.py
+++ b/src/exo/worker/engines/mlx/utils_mlx.py
@@ -285,10 +285,12 @@ def get_eos_token_ids_for_model(model_id: ModelId) -> list[int] | None:
    model_id_lower = model_id.lower()
    if "kimi-k2" in model_id_lower:
        return [163586]
-    elif "glm-4.7-flash" in model_id_lower:
+    elif "glm-5" in model_id_lower or "glm-4.7" in model_id_lower:
+        # For GLM-5 and GLM-4.7
        # 154820: <|endoftext|>, 154827: <|user|>, 154829: <|observation|>
        return [154820, 154827, 154829]
    elif "glm" in model_id_lower:
+        # For GLM-4.5 and older
        return [151336, 151329, 151338]
    return None

--- a/src/exo/worker/runner/runner_supervisor.py
+++ b/src/exo/worker/runner/runner_supervisor.py
@@ -191,7 +191,7 @@ class RunnerSupervisor:
        logger.info("Checking runner's status")
        if self.runner_process.is_alive():
            logger.info("Runner was found to be alive, attempting to join process")
-            await to_thread.run_sync(self.runner_process.join, 1)
+            await to_thread.run_sync(self.runner_process.join, 5)
        rc = self.runner_process.exitcode
        logger.info(f"RunnerSupervisor exited with exit code {rc}")
        if rc == 0:
--- a/uv.lock
+++ b/uv.lock
@@ -377,8 +377,8 @@ dependencies = [
    { name = "hypercorn", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "loguru", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "mflux", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", extra = ["cpu"], marker = "sys_platform == 'linux'" },
+    { name = "mlx", version = "0.30.6", source = { registry = "https://pypi.org/simple" }, extra = ["cpu"], marker = "sys_platform == 'linux'" },
+    { name = "mlx", version = "0.30.7.dev20260218+14841977", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#1484197707f35186ad3bd614357c7c47fdf86ebc" }, marker = "sys_platform == 'darwin'" },
    { name = "mlx-lm", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "msgspec", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "openai-harmony", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -416,9 +416,9 @@ requires-dist = [
    { name = "hypercorn", specifier = ">=0.18.0" },
    { name = "loguru", specifier = ">=0.7.3" },
    { name = "mflux", specifier = "==0.15.5" },
-    { name = "mlx", marker = "sys_platform == 'darwin'", specifier = "==0.30.6" },
+    { name = "mlx", marker = "sys_platform == 'darwin'", git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks" },
    { name = "mlx", extras = ["cpu"], marker = "sys_platform == 'linux'", specifier = "==0.30.6" },
-    { name = "mlx-lm", specifier = "==0.30.6" },
+    { name = "mlx-lm", specifier = "==0.30.7" },
    { name = "msgspec", specifier = ">=0.19.0" },
    { name = "openai-harmony", specifier = ">=0.0.8" },
    { name = "pillow", specifier = ">=11.0,<12.0" },
@@ -1020,8 +1020,8 @@ dependencies = [
    { name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "huggingface-hub", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "matplotlib", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", extra = ["cuda13"], marker = "sys_platform == 'linux'" },
+    { name = "mlx", version = "0.30.6", source = { registry = "https://pypi.org/simple" }, extra = ["cuda13"], marker = "sys_platform == 'linux'" },
+    { name = "mlx", version = "0.30.7.dev20260218+14841977", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#1484197707f35186ad3bd614357c7c47fdf86ebc" }, marker = "sys_platform == 'darwin'" },
    { name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "opencv-python", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "piexif", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -1048,18 +1048,12 @@ wheels = [
 name = "mlx"
 version = "0.30.6"
 source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "mlx-metal", marker = "sys_platform == 'darwin'" },
+resolution-markers = [
+    "sys_platform == 'linux'",
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ae/5b/e460e144a34d5529e010056cccf50b538d56ed001473bc6b246018fd58cb/mlx-0.30.6-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:ed86f8bffc174c2f259ca589ea25464c96cf69d1bb457074a2bf2ef53737e54f", size = 573515, upload-time = "2026-02-06T03:45:23.405Z" },
-    { url = "https://files.pythonhosted.org/packages/60/25/69833fefb9a3fef30b56792b1bcd022496c4fea83e45411d289b77ef7546/mlx-0.30.6-cp313-cp313-macosx_15_0_arm64.whl", hash = "sha256:c52294958269e20f300639a17c1900ca8fc737d859ddda737f9811e94bd040e5", size = 573516, upload-time = "2026-02-06T03:45:24.618Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/6a/7e7fbeebc5cb51b6a5eba96b263a6298707bcbdc059f4b0b73e088bc3dea/mlx-0.30.6-cp313-cp313-macosx_26_0_arm64.whl", hash = "sha256:b5b6636f7c49a4d86d8ec82643b972f45a144a7a9f3a967b27b2e6e22cf71e6a", size = 573592, upload-time = "2026-02-06T03:45:25.928Z" },
    { url = "https://files.pythonhosted.org/packages/93/06/280f6f2ba80520a7109730425eda0d966658793aa0d02d8be8d351f75253/mlx-0.30.6-cp313-cp313-manylinux_2_35_aarch64.whl", hash = "sha256:67e6c9e30a9faeacc209917ef5523177cf9b086914b6b5d83ff886e4294b727d", size = 622011, upload-time = "2026-02-06T03:45:28.165Z" },
    { url = "https://files.pythonhosted.org/packages/fe/35/f872afbee9c079cc69924d9e9c46f5663adb7da58cba3511db082dd307c1/mlx-0.30.6-cp313-cp313-manylinux_2_35_x86_64.whl", hash = "sha256:47db8b16fcb6f6c5a47c0bdb24ed377b41237017ac93aa6cb6aa206c9bdf82e4", size = 663650, upload-time = "2026-02-06T03:45:30.315Z" },
-    { url = "https://files.pythonhosted.org/packages/60/23/361dc7a5797634e4d7e9bdd6564c6b28f9b1246672632def2f91bf066b18/mlx-0.30.6-cp314-cp314-macosx_14_0_arm64.whl", hash = "sha256:78804a89dcff4a838f7c2da72392fe87a523e95122a3c840e53df019122aad45", size = 575028, upload-time = "2026-02-06T03:45:31.549Z" },
-    { url = "https://files.pythonhosted.org/packages/a8/69/1854484d414171586814dfbe8def95f75c4ea2c7341ba13ba8ee675f7c62/mlx-0.30.6-cp314-cp314-macosx_15_0_arm64.whl", hash = "sha256:ec13584ab069665cc7ad34a05494d9291cd623aef6ae96be48875fc87cfc25d6", size = 575026, upload-time = "2026-02-06T03:45:33.072Z" },
-    { url = "https://files.pythonhosted.org/packages/6b/b8/3adbc441924209a7e4c568308b2a0b54bd09aee6a68db5bae85304791e54/mlx-0.30.6-cp314-cp314-macosx_26_0_arm64.whl", hash = "sha256:b2c5e8a090a753ef99a1380a4d059c983083f36198864f6df9faaf1223d083df", size = 575041, upload-time = "2026-02-06T03:45:34.814Z" },
    { url = "https://files.pythonhosted.org/packages/3f/54/9d9e06804fb2088202a2cdf60458e00b221f71420bea285720b60f9e82b5/mlx-0.30.6-cp314-cp314-manylinux_2_35_aarch64.whl", hash = "sha256:9ceddede4af0de31d1f6b3099f70e5469d60cd7c546975dedbdbeab3519cab3f", size = 624002, upload-time = "2026-02-06T03:45:36Z" },
    { url = "https://files.pythonhosted.org/packages/42/92/3140a15a50cb1f9267a6552171e1dfa577861de53e093124bc43707f2a0e/mlx-0.30.6-cp314-cp314-manylinux_2_35_x86_64.whl", hash = "sha256:4a6ffd2d16728cf95f63a1b555d7c2eaeea686a0e6b73228bd265411cb5d77a4", size = 663569, upload-time = "2026-02-06T03:45:37.242Z" },
 ]
@@ -1072,6 +1066,14 @@ cuda13 = [
    { name = "mlx-cuda-13", marker = "sys_platform == 'linux'" },
 ]

+[[package]]
+name = "mlx"
+version = "0.30.7.dev20260218+14841977"
+source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#1484197707f35186ad3bd614357c7c47fdf86ebc" }
+resolution-markers = [
+    "sys_platform == 'darwin'",
+]
+
 [[package]]
 name = "mlx-cpu"
 version = "0.30.6"
@@ -1098,30 +1100,20 @@ wheels = [

 [[package]]
 name = "mlx-lm"
-version = "0.30.6"
+version = "0.30.7"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "jinja2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "mlx", marker = "sys_platform == 'darwin'" },
+    { name = "mlx", version = "0.30.7.dev20260218+14841977", source = { git = "https://github.com/rltakashige/mlx-jaccl-fix-small-recv.git?branch=address-rdma-gpu-locks#1484197707f35186ad3bd614357c7c47fdf86ebc" }, marker = "sys_platform == 'darwin'" },
    { name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "protobuf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "pyyaml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "sentencepiece", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
    { name = "transformers", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/76/cb/815deddc8699b1f694d7e1f9cbed52934c03a8b49432c8add72932bb2f0b/mlx_lm-0.30.6.tar.gz", hash = "sha256:807e042d7040268f1b19190b7eaefd8b2efbff5590a65460974ad4225b91dda1", size = 271733, upload-time = "2026-02-04T21:27:45.741Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/66/0d/56542e2ae13ec6f542d3977d7cff89a205d4f6c5122e0ce23f33265f61c9/mlx_lm-0.30.7.tar.gz", hash = "sha256:e5f31ac58d9f2381f28e1ba639ff903e64f7cff1bdc245c0bc97f72264be329c", size = 275764, upload-time = "2026-02-12T18:41:11.86Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/20/5f/01d281f1fa8a1521d5936659beb4f5ab1f32b463d059263cf9d4cef969d9/mlx_lm-0.30.6-py3-none-any.whl", hash = "sha256:a7405bd581eacc4bf8209d7a6b7f23629585a0d7c6740c2a97e51fee35b3b0e1", size = 379451, upload-time = "2026-02-04T21:27:43.222Z" },
-]
-
-[[package]]
-name = "mlx-metal"
-version = "0.30.6"
-source = { registry = "https://pypi.org/simple" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/f3/85/44406b521f920248fad621334d4dc15e77660a494edf890e7cbee33bf38d/mlx_metal-0.30.6-py3-none-macosx_14_0_arm64.whl", hash = "sha256:ea6d0c973def9a5b4f652cc77036237db3f88c9d0af63701d76b5fddde99b820", size = 38437818, upload-time = "2026-02-06T03:44:56.19Z" },
-    { url = "https://files.pythonhosted.org/packages/d0/cb/10a516995f7d0c154b0d7e633c54b51e96977a86a355105b6474cfcbe0d0/mlx_metal-0.30.6-py3-none-macosx_15_0_arm64.whl", hash = "sha256:0f8cb94634d07e06a372d6ad9a090f38a18bab1ff19a140aede60eacf707bb94", size = 38433701, upload-time = "2026-02-06T03:44:59.678Z" },
-    { url = "https://files.pythonhosted.org/packages/4c/7d/70cb272f7373c334709f210ed8420511fc9d64d05a7a646c0b3b94c29c04/mlx_metal-0.30.6-py3-none-macosx_26_0_arm64.whl", hash = "sha256:d761ae26304f2c4b454eeea7f612a56919d9e5e57dbb1dc0788f8e34aa6f41c2", size = 47718448, upload-time = "2026-02-06T03:45:03.133Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/17/a41c798a3d9cbdc47f39c6db5bba4c2cd199203ead26bf911cb03b644070/mlx_lm-0.30.7-py3-none-any.whl", hash = "sha256:17442a4bf01c4c2d3bca1e647712fe44f19890c3f1eadc8589d389e57b44b9bf", size = 386591, upload-time = "2026-02-12T18:41:10.236Z" },
 ]

 [[package]]
Author	SHA1	Message	Date
Ryuichi Leo Takashige	ea5fc8125f	Address comment	2026-02-18 16:06:30 +00:00
rltakashige	14da9c3f59	Merge branch 'main' into leo/add-glm-5	2026-02-18 13:31:04 +00:00
Evan	5cbd6377a2	prioritize official model cards over custom model cards our old model card search path would override official model cards with custom model cards - our packaged model cards should always be the default here	2026-02-18 13:20:05 +00:00
Ryuichi Leo Takashige	242067e8eb	Update mlx to the nuclear solution	2026-02-18 13:17:39 +00:00
Ryuichi Leo Takashige	03267171ea	move mx_barrier to right before prefill	2026-02-18 12:40:31 +00:00
Ryuichi Leo Takashige	080995a409	try a longer join timeout to prevent crashes on instance deletion	2026-02-18 12:34:05 +00:00
Ryuichi Leo Takashige	0d92d001e6	wrong model card	2026-02-18 12:00:40 +00:00
Ryuichi Leo Takashige	0287ad71a1	format and lint	2026-02-18 11:51:30 +00:00
Ryuichi Leo Takashige	82ac16cc0f	format and lint	2026-02-18 11:48:45 +00:00
Ryuichi Leo Takashige	d78dd516f3	bad diffs 2	2026-02-18 11:47:55 +00:00
Ryuichi Leo Takashige	5c154d091d	bad diffs	2026-02-18 11:45:41 +00:00
rltakashige	e4e0517627	Merge branch 'main' into leo/add-glm-5	2026-02-18 11:44:43 +00:00
Ryuichi Leo Takashige	b28c1d9e92	Merge branch 'main' into leo/add-glm-5 # Conflicts: # pyproject.toml # src/exo/worker/runner/runner.py # uv.lock	2026-02-18 11:43:38 +00:00
Evan Quiney	8f01523ddb	remove dead code (#1496 )	2026-02-18 11:43:27 +00:00
Alex Cheema	3addeadea8	Update mlx-lm to 0.30.7 (#1520 ) ## Summary - Bumps `mlx-lm` from 0.30.6 to 0.30.7 in `pyproject.toml` and `uv.lock` ## Test plan - [x] `uv lock` resolves successfully - [x] `basedpyright` — no new errors (63 pre-existing in unrelated `test_tool_call_tracker.py`) - [x] `ruff check` — all checks passed - [x] `nix fmt` — no formatting changes - [x] `pytest` — 188 passed, 1 skipped 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-18 11:14:23 +00:00
rltakashige	f2be929211	Leo/address rdma gpu locks 2 (#1515 ) Same as #1489 . Had to revert and redo thanks to Claude. --------- Co-authored-by: Jake Hillion <jake@hillion.co.uk> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-17 14:00:52 -08:00
rltakashige	83af8c63fa	Revert "Use custom fork that resolves GPU locks" (#1502 ) Reverts exo-explore/exo#1489 Goddammit Claude...	2026-02-17 18:18:54 +00:00
Evan Quiney	eccc6298d1	Revert "Add MetaInstance declarative layer (#1447 )" This reverts commit `a962a28afc`.	2026-02-17 18:11:47 +00:00
Evan Quiney	c8997217cf	Revert "feat: better onboarding UX for new users (#1479 )" This reverts commit `490d2e46ba`.	2026-02-17 18:02:32 +00:00
Alex Cheema	490d2e46ba	feat: better onboarding UX for new users (#1479 ) ## Summary - Auto-open dashboard in browser on first launch (uses `~/.exo/.dashboard_opened` marker) - Welcome overlay with "Choose a Model" CTA button when no model instance is running - Tutorial progress messages during model download → loading → ready lifecycle stages - Fix conversation sidebar text contrast — bumped to white text, added active state background - Simplify technical jargon — sharding/instance type/min nodes hidden behind collapsible "Advanced Options" toggle; strategy display hidden behind debug mode - Polished DMG installer with drag-to-Applications layout, custom branded background, and AppleScript-configured window positioning ## Test plan - [ ] Launch exo for the first time (delete `~/.exo/.dashboard_opened` to simulate) — browser should auto-open - [ ] Verify welcome overlay appears on topology when no model is loaded - [ ] Launch a model and verify download/loading/ready messages appear in instance cards - [ ] Check conversation sidebar text is readable (white on dark, yellow when active) - [ ] Verify "Advanced Options" toggle hides/shows sharding controls - [ ] Build DMG with `packaging/dmg/create-dmg.sh` and verify drag-to-Applications layout 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-17 17:52:49 +00:00
rltakashige	facf2d4d03	Use custom fork that resolves GPU locks (#1489 ) ## Motivation There is an issue on Macs that means that an explicit synchronization is necessary for memory to be updated from L1 cache. This means that GPU locks can occur when a spin wait does not see the updated timestamp. ## Changes Updated in my own personal fork. ## Why It Works https://github.com/ARM-software/acle/releases ## Test Plan ### Manual Testing Tested manually that no GPU locks occur (even with multiple simultaneous instances running) and that the performance differential is negligible (267 vs 269 tps on Llama 3.2 1B at an approx 10k context.) ------------------------------------------------------ I have seen a GPU lock, specifically when sending a particularly large chat completion while the model was loading. However, I have since been unable to reproduce and this may be something I did wrong. Please do create an issue and tag me if any GPU locks do occur. --------- Co-authored-by: Jake Hillion <jake@hillion.co.uk> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-17 17:48:43 +00:00
Alex Cheema	a962a28afc	Add MetaInstance declarative layer (#1447 ) ## Motivation Users currently manage instances directly, which means if a node disconnects or connections break, the instance dies and nothing recreates it. MetaInstance is a declarative primitive: "ensure an instance matching these parameters always exists." The reconciler watches for unhealthy or missing backing instances and re-places them automatically. ## Changes - MetaInstance type (`meta_instance.py`): declarative constraint with `model_id`, `min_nodes`, optional `node_ids`, and `sharding` - Reconciler (`reconcile.py`): `find_unsatisfied_meta_instances` checks which MetaInstances lack a healthy backing instance, `try_place_for_meta_instance` creates one - Master loop (`main.py`): periodically reconciles unsatisfied MetaInstances; immediate placement on `CreateMetaInstance` command - API (`api.py`): `create_meta_instance` / `delete_meta_instance` / `GET /meta_instances` endpoints; delete cascades to backing instances with task cancellation - Binding via `meta_instance_id` on Instance (`instances.py`): no separate binding event or backing map — the instance carries its parent MetaInstance ID directly, eliminating race conditions in the reconciler - Dashboard: sidebar shows MetaInstances with their backing instance status; orphan instances (created directly) still shown separately - Tests: constraint matching, connection health, unsatisfied detection, exclusive binding, cascade delete with task cancellation ### Recent improvements - fix: cancel active tasks on cascade delete — `DeleteMetaInstance` now emits `TaskStatusUpdated(Cancelled)` for any Pending/Running tasks on backing instances before emitting `InstanceDeleted`. Previously, cascade-deleting backing instances left orphaned task references in state. - Lifecycle logging — added `logger.info`/`logger.warning` for: `CreateMetaInstance` (model, min_nodes, sharding), `DeleteMetaInstance` (with cascade count), reconciler placement success/failure, and retry decisions with attempt counts in `InstanceHealthReconciler`. - GET `/meta_instances` endpoint — lists all meta-instances without needing to fetch full state. - 2 regression tests — `test_cascade_delete_cancels_active_tasks` and `test_cascade_delete_skips_completed_tasks` verify the cascade-delete event sequence. ## Why It Works Putting `meta_instance_id` on `BaseInstance` makes binding inherent to instance creation. When the reconciler creates an instance for a MetaInstance, it tags it via `model_copy`. When the instance is deleted, the binding disappears with it. This avoids the two bugs that a separate binding mechanism would introduce: 1. Stale exclusion sets — the reconciler loop can't accidentally bind two MetaInstances to the same instance 2. Delete ordering race — no window between deleting an instance and its binding where the reconciler could re-place ## Test Plan ### Manual Testing <!-- Hardware: (e.g., MacBook Pro M1 Max 32GB, Mac Mini M2 16GB, connected via Thunderbolt 4) --> - Created MetaInstance via dashboard, verified instance placed - Verified delete cascades (deleting MetaInstance removes backing instance) - Verified orphan instances still work independently ### Automated Testing - 30 tests in `test_meta_instance_edge_cases.py`: lifecycle, retry logic, error handling, concurrent operations, cascade delete with task cancellation - 24 tests in `test_reconcile.py`: constraint matching, connection health (single/multi-node, edge removal, IP changes), unsatisfied detection, exclusive binding, idempotency - All 261 tests pass - basedpyright 0 errors, ruff clean, dashboard builds --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>	2026-02-17 09:48:19 -08:00
Alex Cheema	db79c350c1	Fix graceful process shutdown in macOS app (#1372 ) ## Motivation Fixes #1370 When the macOS app stops exo, GPU/system memory isn't released. This happens because: 1. The macOS app calls `process.terminate()` (SIGTERM) but the Python process only registers a graceful shutdown handler for SIGINT, not SIGTERM. SIGTERM's default Python behavior raises `SystemExit` which bypasses the cleanup cascade (runner subprocess MLX cleanup via `mx.clear_cache()`, channel closing, etc.). 2. The app doesn't wait for the process to actually finish cleanup — it immediately nils out the process reference. ## Changes `src/exo/main.py`: Register SIGTERM handler alongside SIGINT so the graceful shutdown cascade (`Node.shutdown()` → cancel task group → worker/runner cleanup → `mx.clear_cache()` + `gc.collect()`) runs regardless of which signal is received. `app/EXO/EXO/ExoProcessController.swift`: Replace immediate `process.terminate()` with escalating shutdown per @Evanev7's suggestion: 1. Send SIGINT via `process.interrupt()` — triggers the registered Python handler for graceful cleanup 2. Wait up to 5 seconds for the process to exit 3. If still running, escalate to SIGTERM via `process.terminate()` 4. Wait up to 3 seconds 5. If still running, force kill via SIGKILL The escalation runs in a detached `Task` so the UI updates immediately (status → stopped) without blocking. ## Why It Works The root cause is that SIGTERM wasn't triggering the graceful shutdown path. By registering a SIGTERM handler in Python and sending SIGINT first from the macOS app, the process gets a chance to run the full cleanup cascade: cancelling the task group, shutting down runners (which call `del model; mx.clear_cache(); gc.collect()`), closing channels, and flushing logs. The escalation to SIGTERM and SIGKILL ensures the process always terminates even if graceful shutdown hangs. ## Test Plan ### Manual Testing <!-- Hardware: Mac Studio M4 Max 128GB --> - Start exo via macOS app, load a model, run inference - Stop via the toggle switch, verify memory is released without requiring a system restart - Test rapid stop/start (restart) to ensure no race conditions ### Automated Testing - `uv run basedpyright` — 0 errors - `uv run ruff check` — passes - `nix fmt` — no changes --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com> Co-authored-by: Evan Quiney <evanev7@gmail.com>	2026-02-17 09:03:54 -08:00
Ryuichi Leo Takashige	58e751a930	revert	2026-02-13 20:50:27 +00:00
Ryuichi Leo Takashige	6718da7af3	try optimisations	2026-02-13 19:54:23 +00:00
Ryuichi Leo Takashige	9d9237f68f	delete unnecessary files	2026-02-13 19:54:08 +00:00
Ryuichi Leo Takashige	8de4e10736	fix depends for CacheList	2026-02-13 15:29:53 +00:00
Ryuichi Leo Takashige	0de3e486df	update glm 5 to use upstream mlx lm	2026-02-13 12:50:08 +00:00
Ryuichi Leo Takashige	ce0eef999e	return to mlx lm main	2026-02-13 12:31:07 +00:00
Ryuichi Leo Takashige	20fb6a9acc	handle absolute paths	2026-02-13 11:09:46 +00:00
Ryuichi Leo Takashige	4a1234106b	add type stub	2026-02-12 23:46:13 +00:00
Ryuichi Leo Takashige	2929249147	fix glm eos id	2026-02-12 23:46:13 +00:00
Ryuichi Leo Takashige	837ffc6b97	dont patch glm5 tokenizer?	2026-02-12 23:46:13 +00:00
Ryuichi Leo Takashige	2366ed0299	add glm5 model cards	2026-02-12 23:46:13 +00:00
Ryuichi Leo Takashige	c95c088952	convert glm5	2026-02-12 23:46:13 +00:00
Ryuichi Leo Takashige	2af1c81cde	convert glm5	2026-02-12 23:46:13 +00:00
Ryuichi Leo Takashige	6922dd4ead	download faster	2026-02-12 23:46:13 +00:00
Ryuichi Leo Takashige	8c2fb7f130	Add tensor sharding	2026-02-12 23:46:13 +00:00
Ryuichi Leo Takashige	0488cb2967	update pyproject.toml	2026-02-12 23:46:13 +00:00