llama.cpp/tests/test-backend-ops.cpp at 8c660242d708d3913a2adc2b6e4a9ee9cf5e4ce7

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-02 09:12:03 +00:00

Files

Johannes Gäßler a743d76a01 CUDA: generalize FP16 fattn vec kernel (#7061 )

* CUDA: generalize FP16 fattn vec kernel

* disable unsupported head sizes for AMD in test

* try AMD fix

* fix batch size 2-8

* partially revert changes

2024-05-09 14:32:02 +02:00

81 KiB

Raw Blame History

View Raw

81 KiB Raw Blame History

81 KiB

Raw Blame History