Skip to content

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

C

Fix CUDA detection on Windows: cuda_binary()/cuda_linkage() always returned False

Stonki13d2d3a7b5598f
diff --git a/c/coli b/c/coli
index 4c274159..4566ea64 100755
--- a/c/coli
+++ b/c/coli
@@ -141,12 +141,24 @@ 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))
diff --git a/c/doctor.py b/c/doctor.py
index 4cb5a42e..cbe9c870 100644
--- a/c/doctor.py
+++ b/c/doctor.py
@@ -19,16 +19,33 @@ def _check(identifier, status, summary, **details):
def cuda_linkage(engine_path):
"""Return CUDA linkage state without loading the executable or CUDA runtime."""
- if not Path(engine_path).is_file() or os.name != "posix":
- return {"linked": False, "missing": False}
- try:
- result = subprocess.run(["ldd", str(engine_path)], capture_output=True, text=True,
- timeout=3, check=False)
- except (OSError, subprocess.SubprocessError):
+ engine = Path(engine_path)
+ if not engine.is_file():
return {"linked": False, "missing": False}
- lines = [line for line in result.stdout.splitlines() if "libcudart" in line]
- return {"linked": any("not found" not in line for line in lines),
- "missing": any("not found" in line for line in lines)}
+ if os.name == "posix":
+ try:
+ result = subprocess.run(["ldd", str(engine)], capture_output=True, text=True,
+ timeout=3, check=False)
+ except (OSError, subprocess.SubprocessError):
+ return {"linked": False, "missing": False}
+ lines = [line for line in result.stdout.splitlines() if "libcudart" in line]
+ return {"linked": any("not found" not in line for line in lines),
+ "missing": any("not found" in line for line in lines)}
+ 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:
+ built = b"[CUDA] mode: routed experts" in engine.read_bytes()
+ except OSError:
+ return {"linked": False, "missing": False}
+ if not built:
+ return {"linked": False, "missing": False}
+ dll_present = (engine.parent / "coli_cuda.dll").is_file()
+ return {"linked": dll_present, "missing": not dll_present}
+ return {"linked": False, "missing": False}
def run_doctor(model, ram_gb=0, context=4096, gpu_indices=None, vram_gb=0, *,