HaimAshk
commented
1 month ago Was a compilation problem I missed. Solved by recompiling.
Closed HaimAshk closed 1 month ago
HaimAshk
commented
1 month ago Was a compilation problem I missed. Solved by recompiling.
Expected Behavior
Current Behavior
When using the ProstT5 model and --gpu 1 I get the error: Error loading ProstT5: DriverError(CUDA_ERROR_INVALID_PTX, "a PTX JIT compilation failed") when loading cast_f32_f16 The same command runs OK on CPU
Foldssek Output (for bugs)
foldseek easy-search test_arabidopsis_alphafold.fas Arabidopsis_thaliana_taxid_3702_AlphaFold_v3.AlphaFold.foldseekdb test_arabidopsis_alphafold.result.m8 /tmp/hashkenazy/foldseek_Prost5/tmp --prostt5-model /ebio/scratch/hashkenazy/foldseek_9_Prost5_model/weights --format-output query,target,evalue,fident,nident,qstart,qend,qlen,tstart,tend,tlen,alnlen,bits,qheader,theader,mismatch,qcov,tcov --max-seqs 50000 --gpu 1 easy-search test_arabidopsis_alphafold.fas Arabidopsis_thaliana_taxid_3702_AlphaFold_v3.AlphaFold.foldseekdb test_arabidopsis_alphafold.result.m8 /tmp/hashkenazy/foldseek_Prost5/tmp --prostt5-model /ebio/scratch/hashkenazy/foldseek_9_Prost5_model/weights --format-output query,target,evalue,fident,nident,qstart,qend,qlen,tstart,tend,tlen,alnlen,bits,qheader,theader,mismatch,qcov,tcov --max-seqs 50000 --gpu 1
MMseqs Version: bc212bc8602ef426c7b58368c65dd744443f802c Seq. id. threshold 0 Coverage threshold 0 Coverage mode 0 Max reject 2147483647 Max accept 2147483647 Add backtrace false TMscore threshold 0 TMalign hit order 0 TMalign fast 1 Preload mode 0 Threads 128 Verbosity 3 LDDT threshold 0 Sort by structure bit score 1 Alignment type 2 Exact TMscore 0 Substitution matrix aa:3di.out,nucl:3di.out Alignment mode 3 Alignment mode 0 E-value threshold 10 Min alignment length 0 Seq. id. mode 0 Alternative alignments 0 Max sequence length 65535 Compositional bias 1 Compositional bias 1 Gap open cost aa:10,nucl:10 Gap extension cost aa:1,nucl:1 Compressed 0 Seed substitution matrix aa:3di.out,nucl:3di.out Sensitivity 9.5 k-mer length 6 Target search mode 0 k-score seq:2147483647,prof:2147483647 Max results per query 50000 Split database 0 Split mode 2 Split memory limit 0 Diagonal scoring true Exact k-mer matching 0 Mask residues 0 Mask residues probability 0.99995 Mask lower case residues 1 Minimum diagonal score 30 Selected taxa
Spaced k-mers 1 Spaced k-mer pattern
Local temporary path
Exhaustive search mode false Prefilter mode 0 Search iterations 1 Remove temporary files true MPI runner
Force restart with latest tmp false Cluster search 0 Use GPU 1 Path to ProstT5 /ebio/scratch/hashkenazy/foldseek_9_Prost5_model/weights Chain name mode 0 Write mapping file 0 Mask b-factor threshold 0 Coord store mode 2 Write lookup file 1 Input format 0 File Inclusion Regex .* File Exclusion Regex ^$ Alignment format 0 Format alignment output query,target,evalue,fident,nident,qstart,qend,qlen,tstart,tend,tlen,alnlen,bits,qheader,theader,mismatch,qcov,tcov Database output false Greedy best hits false
createdb test_arabidopsis_alphafold.fas /tmp/hashkenazy/foldseek_Prost5/tmp/4959022769211143606/query --gpu 1 --prostt5-model /ebio/scratch/hashkenazy/foldseek_9_Prost5_model/weights --chain-name-mode 0 --write-mapping 0 --mask-bfactor-threshold 0 --coord-store-mode 2 --write-lookup 1 --input-format 0 --file-include '.*' --file-exclude '^$' --threads 128 -v 3
Converting sequences
Time for merging to query_h: 0h 0m 0s 1ms Time for merging to query: 0h 0m 0s 1ms Database type: Aminoacid Error loading ProstT5: DriverError(CUDA_ERROR_INVALID_PTX, "a PTX JIT compilation failed") when loading cast_f32_f16 Time for processing: 0h 0m 0s 992ms Error: query createdb died
Context
Providing context helps us come up with a solution and improve our documentation for the future.
Your Environment
Include as many relevant details about the environment you experienced the bug in.
Thanks in advance for any advice!