[Model][Hardware][AMD][Kernel] Part 2/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_ATTN (#42755)

Signed-off-by: Jack Hu <Jack.Hu@amd.com>
Signed-off-by: Jack Hu <jingxujaster@hotmail.com>
Signed-off-by: Jack Hu <jack.hu@amd.com>
Co-authored-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
This commit is contained in:
Jack Hu
2026-10-15 17:10:14 -07:00
committed by GitHub
co-authored by Douglas Lehr
parent af28c171f5
commit ef38e8d006
23 changed files with 701 additions and 205 deletions
@@ -893,6 +893,7 @@ class QkNormRopeKvCacheFusionPass(VllmPatternMatcherPass):
layer.head_size,
)
continue
layer.impl.set_interleaved_v_cache()
if supports_rope:
for epsilon in [1e-5, 1e-6]:
for neox in [True, False]:
@@ -903,7 +904,6 @@ class QkNormRopeKvCacheFusionPass(VllmPatternMatcherPass):
is_neox=neox,
quant_query=quant_q,
).register(self.patterns)
if supports_mrope:
for section, is_interleaved in self.mrope_configs:
rotary_dim = 2 * sum(section)