Try multiple endpoints for internet connectivity check

Some ISPs/networks block connections to 1.1.1.1, causing exo to
incorrectly report no internet connectivity and fail to download
models. Try 1.1.1.1, 8.8.8.8, and 1.0.0.1 in sequence, succeeding
if any responds.

Fixes #1425

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

resources/inference_model_cards/mlx-community--GLM-5-4bit.toml

@@ -1,12 +0,0 @@
-model_id = "mlx-community/GLM-5-4bit"
-n_layers = 78
-hidden_size = 6144
-supports_tensor = true
-tasks = ["TextGeneration"]
-family = "glm"
-quantization = "4bit"
-base_model = "GLM 5"
-capabilities = ["text", "thinking"]
-
-[storage_size]
-in_bytes = 418621403136

resources/inference_model_cards/mlx-community--GLM-5-8bit-MXFP8.toml

@@ -1,12 +0,0 @@
-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 = 767273926656

resources/inference_model_cards/mlx-community--GLM-5-MXFP4-Q8.toml

@@ -1,12 +0,0 @@
-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 = 405480321024

resources/inference_model_cards/mlx-community--GLM-5.toml

@@ -1,12 +0,0 @@
-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

src/exo/download/coordinator.py

@@ -116,14 +116,17 @@ class DownloadCoordinator:
             tg.start_soon(self._check_internet_connection)
 
     def _test_internet_connection(self) -> None:
-        try:
-            socket.create_connection(("1.1.1.1", 443), timeout=3).close()
-            self.shard_downloader.set_internet_connection(True)
-        except OSError:
-            self.shard_downloader.set_internet_connection(False)
-        logger.debug(
-            f"Internet connectivity: {self.shard_downloader.internet_connection}"
-        )
+        # Try multiple endpoints since some ISPs/networks block specific IPs
+        for host in ("1.1.1.1", "8.8.8.8", "1.0.0.1"):
+            try:
+                socket.create_connection((host, 443), timeout=3).close()
+                self.shard_downloader.set_internet_connection(True)
+                logger.debug(f"Internet connectivity: True (via {host})")
+                return
+            except OSError:
+                continue
+        self.shard_downloader.set_internet_connection(False)
+        logger.debug("Internet connectivity: False")
 
     async def _check_internet_connection(self) -> None:
         first_connection = True

src/exo/shared/models/model_cards.py

@@ -182,7 +182,6 @@ class ConfigData(BaseModel):
     def supports_tensor(self) -> bool:
         return self.architectures in [
             ["Glm4MoeLiteForCausalLM"],
-            ["GlmMoeDsaForCausalLM"],
             ["DeepseekV32ForCausalLM"],
             ["DeepseekV3ForCausalLM"],
             ["Qwen3NextForCausalLM"],

src/exo/worker/engines/mlx/utils_mlx.py

@@ -285,7 +285,7 @@ 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-5" in model_id_lower or "glm-4.7" in model_id_lower:
+    elif "glm-4.7-flash" in model_id_lower:
         # 154820: <|endoftext|>, 154827: <|user|>, 154829: <|observation|>
         return [154820, 154827, 154829]
     elif "glm" in model_id_lower: