NVTX missing using SE3nv.yml -- Pytorch 2.0 solution about rfdiffusion HOT 4 OPEN

OS: Fedora36
GPU: gtx 1080Ti

I have CUDA 11.8, but your solution worked after I modified the SE3nv.yml to have:

- cudatoolkit=11.7
- dgl-cuda11.7

Note, I had to accept one version lower on the installed toolkit because there is currently no dgl-cuda11.8

from rfdiffusion.

I got it too, and for me this worked:

conda (or mamba) update --all -c pytorch

from rfdiffusion.

I also ran across this issue and your solution seems to works (at least on the examples I've tried). Thanks!

from rfdiffusion.

The solution: $ pip3 install --force-reinstall torch torchvision torchaudio
worked for me too on RTX4090 on Ubuntu 22.04 I was getting slightly different error though:

Traceback (most recent call last):
File "/big18TB/apps/RF/RFdiffusion/./scripts/run_inference.py", line 94, in main
px0, x_t, seq_t, plddt = sampler.sample_step(
File "/big18TB/apps/RF/RFdiffusion/rfdiffusion/inference/model_runners.py", line 664, in sample_step
msa_prev, pair_prev, px0, state_prev, alpha, logits, plddt = self.model(msa_masked,
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/big18TB/apps/RF/RFdiffusion/rfdiffusion/RoseTTAFoldModel.py", line 102, in forward
msa, pair, R, T, alpha_s, state = self.simulator(seq, msa_latent, msa_full, pair, xyz[:,:,:3],
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/big18TB/apps/RF/RFdiffusion/rfdiffusion/Track_module.py", line 420, in forward
msa_full, pair, R_in, T_in, state, alpha = self.extra_block[i_m](msa_full,
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/big18TB/apps/RF/RFdiffusion/rfdiffusion/Track_module.py", line 332, in forward
R, T, state, alpha = self.str2str(msa, pair, R_in, T_in, xyz, state, idx, motif_mask=motif_mask, top_k=0)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/torch/cuda/amp/autocast_mode.py", line 141, in decorate_autocast
return func(args, **kwargs)
File "/big18TB/apps/RF/RFdiffusion/rfdiffusion/Track_module.py", line 266, in forward
shift = self.se3(G, node.reshape(BL, -1, 1), l1_feats, edge_feats)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/big18TB/apps/RF/RFdiffusion/rfdiffusion/SE3_network.py", line 83, in forward
return self.se3(G, node_features, edge_features)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/se3_transformer-1.0.0-py3.9.egg/se3_transformer/model/transformer.py", line 140, in forward
basis = basis or get_basis(graph.edata['rel_pos'], max_degree=self.max_degree, compute_gradients=False,
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/se3_transformer-1.0.0-py3.9.egg/se3_transformer/model/basis.py", line 167, in get_basis
spherical_harmonics = get_spherical_harmonics(relative_pos, max_degree)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/se3_transformer-1.0.0-py3.9.egg/se3_transformer/model/basis.py", line 58, in get_spherical_harmonics
sh = o3.spherical_harmonics(all_degrees, relative_pos, normalize=True)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/e3nn/o3/_spherical_harmonics.py", line 180, in spherical_harmonics
return sh(x)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/bulat/anaconda3/envs/SE3nv/lib/python3.9/site-packages/e3nn/o3/_spherical_harmonics.py", line 82, in forward
sh = _spherical_harmonics(self._lmax, x[..., 0], x[..., 1], x[..., 2])
RuntimeError: nvrtc: error: invalid value for --gpu-architecture (-arch)

nvrtc compilation failed:

#define NAN __int_as_float(0x7fffffff)
#define POS_INFINITY __int_as_float(0x7f800000)
#define NEG_INFINITY __int_as_float(0xff800000)

template
device T maximum(T a, T b) {
return isnan(a) ? a : (a > b ? a : b);
}

template
device T minimum(T a, T b) {
return isnan(a) ? a : (a < b ? a : b);
}

extern "C" global
void fused_pow_pow_pow_su_9196483836509741110(float* tz_1, float* ty_1, float* tx_1, float* aten_mul, float* aten_mul_1, float* aten_mul_2, float* aten_sub, float* aten_add, float* aten_mul_3, float* aten_pow) {
{
if (512 * blockIdx.x + threadIdx.x<22350 ? 1 : 0) {
float ty_1_1 = __ldg(ty_1 + 3 * (512 * blockIdx.x + threadIdx.x));
aten_pow[512 * blockIdx.x + threadIdx.x] = ty_1_1 * ty_1_1;
float tz_1_1 = __ldg(tz_1 + 3 * (512 * blockIdx.x + threadIdx.x));
float tx_1_1 = __ldg(tx_1 + 3 * (512 * blockIdx.x + threadIdx.x));
aten_mul_3[512 * blockIdx.x + threadIdx.x] = (float)((double)(tz_1_1 * tz_1_1 - tx_1_1 * tx_1_1) * 0.8660254037844386);
aten_add[512 * blockIdx.x + threadIdx.x] = tx_1_1 * tx_1_1 + tz_1_1 * tz_1_1;
aten_sub[512 * blockIdx.x + threadIdx.x] = ty_1_1 * ty_1_1 - (float)((double)(tx_1_1 * tx_1_1 + tz_1_1 * tz_1_1) * 0.5);
aten_mul_2[512 * blockIdx.x + threadIdx.x] = (float)((double)(ty_1_1) * 1.732050807568877) * tz_1_1;
aten_mul_1[512 * blockIdx.x + threadIdx.x] = (float)((double)(tx_1_1) * 1.732050807568877) * ty_1_1;
aten_mul[512 * blockIdx.x + threadIdx.x] = (float)((double)(tx_1_1) * 1.732050807568877) * tz_1_1;
}
}
}

from rfdiffusion.