Stefan Walcz 9b0b7da96e fix(rocm): point *_TENSILE_LIBPATH at the architecture folder (#12411) ...

Newer ROCm releases split the rocBLAS and hipBLASLt TensileLibrary data
into one folder per GPU architecture (lib/hipblaslt/library/gfx1151/...).
The run.sh of the ROCm-capable backends exports ROCBLAS_TENSILE_LIBPATH and
HIPBLASLT_TENSILE_LIBPATH as the parent folder, and both libraries only look
directly in that folder, so they miss every kernel:

  rocblaslt error: Cannot read ".../hipblaslt/library/TensileLibrary_lazy_gfx1151.dat"
  hipModuleLoad failed: .../hipblaslt/library/Kernels.so-000-gfx1151.hsaco

and fall back to slower code paths.

rocm_tensile_dir keeps the folder when it has files at the top level (the
older flat layout) or several architecture folders, and descends into the
architecture folder when the bundle carries exactly one.

Assisted-by: Claude:claude-opus-5-5

Signed-off-by: Stefan Walcz <stefan.walcz@walcz.de>

2026-10-05 01:38:09 +02:00

..

audio-cpp

chore: ⬆️ Update 0xShug0/audio.cpp to 9a02e61326aaaf9d462b584ca5e0daba22c0abfc (#12389)

2026-10-01 08:22:05 +02:00

bonsai

fix(rocm): point *_TENSILE_LIBPATH at the architecture folder (#12411)

2026-10-05 01:38:09 +02:00

ds4

chore: ⬆️ Update antirez/ds4 to 0aaea5a238fb41a35106a551e73c8409dfb751ac (#12168)

2026-09-21 08:26:08 +02:00

grpc

fix: speedup git submodule update with --single-branch (#2847)

2024-07-13 22:32:25 +02:00

ik-llama-cpp

chore: ⬆️ Update ikawrakow/ik_llama.cpp to 5f89bfc81268b4d56d2af63ccbed59de17c64c09 (#12440)

2026-10-02 23:57:20 +02:00

llama-cpp

fix(rocm): point *_TENSILE_LIBPATH at the architecture folder (#12411)

2026-10-05 01:38:09 +02:00

privacy-filter

refactor(backends): extract package-system-libs.sh from 31 package.sh (#11095)

2026-07-30 16:30:49 +02:00

turboquant

fix(rocm): point *_TENSILE_LIBPATH at the architecture folder (#12411)

2026-10-05 01:38:09 +02:00

run-unit-tests.sh

feat(audio-cpp): add the audio.cpp native backend (#11141)

2026-07-30 12:11:56 +02:00