llama.cpp
8bf88ba9 - vulkan: disable subgroup arithmetic on Qualcomm's driver (#30826)

Commit
7 hours ago
vulkan: disable subgroup arithmetic on Qualcomm's driver (#30826) On Adreno, subgroupAdd() after divergent code returns wrong sums. The fused ADD+RMS_NORM partial-sum path hits this, so the decode-step norm is garbage and models emit stray tokens after long prompts. Clear subgroup_arithmetic for the Qualcomm proprietary driver, which also turns off add_rms_fusion and the other subgroupAdd paths. test-backend-ops on Adreno 850 and X2-90: ADD_RMS_NORM 20/25 -> 25/25, RMS_NORM_MUL_ADD 33/45 -> 45/45. llama 3B Q4_0 on Adreno 850: pp512 and tg128 unchanged.
Author
Parents
Loading