Error map:: triton

[kolmogorov-quyet]

/usr/local/lib/python3.10/dist-packages/triton/compiler/backends/cuda.py in make_llir(src, metadata, options, capability)
171 add_external_libs(src, names, paths)
172 # TritonGPU -> LLVM-IR
--> 173 ret = translate_triton_gpu_to_llvmir(src, capability, tma_infos, runtime.TARGET.NVVM)
174 if len(tma_infos) > 0:
175 metadata["tensormaps_info"] = parse_tma_info(tma_infos, metadata["ids_of_folded_args"])

IndexError: map::at
env colab notebook:

%cd hydra
!pip install -r requirements.txt

import torch
from hydra import Hydra

batch, length, dim = 2, 64, 16
x = torch.randn(batch, length, dim).to("cuda")
model = Hydra(
    d_model=dim, # Model dimension d_model
    d_state=64,  # SSM state expansion factor
    d_conv=7,    # Local non-causal convolution width
    expand=2,    # Block expansion factor
    use_mem_eff_path=False,    # Nightly release. Thanks to Alston Lo
    headdim=16,
).to("cuda")
y = model(x)
assert y.shape == x.shape```

[sukjunhwang]

Hi, which triton version is being used?