[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:
@@ -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)
|
||||
|
||||
Reference in New Issue
Block a user