Merge pull request #395 from Stonki13/fix/windows-cuda-detection

Fix CUDA detection on Windows (coli/doctor.py always report CPU-only)

c/coli

@@ -143,12 +143,24 @@ def need_model(model):
         sys.exit(f"{C.yel}engine is not built.{C.r} Run: coli build")
 
 def cuda_binary():
-    if not os.path.exists(GLM) or sys.platform != "linux": return False
-    try:
-        linked=subprocess.run(["ldd",GLM],capture_output=True,text=True,timeout=3)
-        return any("libcudart" in line and "not found" not in line
-                   for line in linked.stdout.splitlines())
-    except (OSError,subprocess.SubprocessError): return False
+    if not os.path.exists(GLM): return False
+    if sys.platform == "linux":
+        try:
+            linked=subprocess.run(["ldd",GLM],capture_output=True,text=True,timeout=3)
+            return any("libcudart" in line and "not found" not in line
+                       for line in linked.stdout.splitlines())
+        except (OSError,subprocess.SubprocessError): return False
+    if sys.platform == "win32":
+        # Windows CUDA_DLL=1 builds never link libcudart directly: glm.exe loads
+        # coli_cuda.dll at runtime via LoadLibrary (backend_loader.c), so there's no
+        # import-table entry for ldd/dumpbin to see. Detect the COLI_CUDA build via a
+        # marker string baked into glm.c's #ifdef COLI_CUDA block instead, and require
+        # coli_cuda.dll to actually sit next to glm.exe (else CUDA init fails at startup).
+        try:
+            with open(GLM,"rb") as f: built=b"[CUDA] mode: routed experts" in f.read()
+        except OSError: return False
+        return built and os.path.exists(os.path.join(os.path.dirname(GLM),"coli_cuda.dll"))
+    return False
 
 def resource_request(a, env):
     ctx=a.ctx or int(env.get("CTX",4096))