[AMD] Enable deepseek-v4 topk_transform v2 kernel (#36684)

This commit is contained in:
Thomas Wang
2026-08-27 22:36:11 -07:00
committed by GitHub
parent cce0b53466
commit baf09f3954
4 changed files with 49 additions and 7 deletions
@@ -34,9 +34,10 @@ from sglang.kernels.ops.attention.dsv4.topk import (
topk_transform_512_v2,
topk_transform_ragged_v2,
)
from sglang.test.ci.ci_register import register_cuda_ci
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
register_cuda_ci(est_time=90, stage="base-b-kernel-unit", runner_config="1-gpu-large")
register_amd_ci(est_time=30, stage="jit-kernel-unit", runner_config="amd")
PAGE_SIZE = 64 # c4 page size = 256 // 4
PAGE_BITS = PAGE_SIZE.bit_length() - 1