Welcome to NVIDIA Parabricks v4.7.1

Bug Fixes

mutectcaller:

  • Added the missing read group (RG) header line in the normal sample BAM/CRAM output defined by --mutect-bam-output.

fq2bam, fq2bam_meth, giraffe, minimap2, markdup, rna_fq2bam, and associated pipelines:

  • Addressed an issue preventing --markdups-assume-sortorder-queryname from taking effect when combined with --gpusort.

deepvariant, deepsomatic, and pangenome_aware_deepvariant:

  • Fixed a potential GPU out-of-memory condition when --num-streams-per-gpu was set to auto (default).

rna_fq2bam:

  • Fixed missing alignments for reads with a high degree of multimapping.

fq2bam and fq2bam_meth:

  • Fixed a memory leak that occurred during CPU recovery.

  • Fixed an issue where --bwa-nstreams auto (default value) and --gpuwrite could potentially run out of device memory with GPUs having more than 16 GB but less than 22 GB of memory.

fq2bam, fq2bam_meth, giraffe, minimap2, rna_fq2bam, bamsort, and associated pipelines:

  • Fixed a potential out-of-bounds device write when using --gpuwrite for accelerated BAM and CRAM writing. This risk was more likely to appear on ARM systems such as NVIDIA GB10.

fq2bam_meth:

  • Fixed --preserve-file-symlinks to work properly with methylation reference genome and indexes.

giraffe:

  • Fixed a potential deadlock in paired-end mode that could occur when an input file had very few batches and all of them entered CPU recovery mode.

minimap2:

  • Fixed an issue where null padding could appear in output query names when using BAM input.

© Copyright 2026, NVIDIA. Last updated on Jul 6, 2026