search

Luke-ebbis / complex-prediction

Complex prediction using combfold
Apache License 2.0
2 stars 1 forks source link

Colab fold does not work #4

Closed Luke-ebbis closed 5 months ago

Luke-ebbis commented 6 months ago 

WARNING: You are welcome to use the default MSA server, however keep in mind that it's a
limited shared resource only capable of processing a few thousand MSAs per day. Please
submit jobs only from a single IP address. We reserve the right to limit access to the
server case-by-case when usage exceeds fair use. If you require more MSAs: You can 
precompute all MSAs with `colabfold_search` or host your own API and pass it to `--host-url`

2024-05-09 14:18:12,464 Running colabfold 1.5.5
2024-05-09 14:18:12,472 non-fasta/a3m file in input directory: ../../../../results/data/subunits/subunits/fasta/.snakemake_timestamp
2024-05-09 14:18:13,275 Unable to initialize backend 'rocm': NOT_FOUND: Could not find registered platform with name: "rocm". Available platform names are: CUDA
2024-05-09 14:18:13,279 Unable to initialize backend 'tpu': INTERNAL: Failed to open libtpu.so: libtpu.so: cannot open shared object file: No such file or directory
2024-05-09 14:18:19,062 Running on GPU
2024-05-09 14:18:21,034 Found 5 citations for tools or databases
2024-05-09 14:18:21,035 Query 1/3: A0_A0 (length 1020)
COMPLETE: 100%|██████████| 150/150 [elapsed: 00:08 remaining: 00:00]
2024-05-09 14:18:34.160109: W external/xla/xla/service/gpu/nvptx_compiler.cc:760] The NVIDIA driver's CUDA version is 12.2 which is older than the ptxas CUDA version (12.4.131). Because the driver is older than the ptxas version, XLA is disabling parallel compilation, which may slow down compilation. You should update your NVIDIA driver or use the NVIDIA-provided CUDA forward compatibility packages.
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
'+ptx84' is not a recognized feature for this target (ignoring feature)
LLVM ERROR: Cannot select: intrinsic %llvm.nvvm.shfl.sync.down.f32
Luke-ebbis commented 6 months ago

I try to alleviate this by re-installing colabfold in the pipeline directly dev-colabfold-install. However I am met with the error that biopython cannot be found...

Luke-ebbis commented 5 months ago

After Andreas updated the cuda version, the pipeline works.