[Hardware][MUSA] Enable Qwen3-Omni ModelOpt FP8 inference (#5671)
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com> Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com> Co-authored-by: amy-why-3459 <wuhaiyan17@huawei.com>
This commit is contained in:
7 files changed
+125
-3
No files matched your search
@@ -155,6 +155,11 @@ class OmniPlatform(Platform):
|
||||
"""Check if the platform supports torch.compile with inductor backend."""
|
||||
raise NotImplementedError
|
||||
|
||||
@classmethod
|
||||
def supports_talker_mtp_graph_capture(cls) -> bool:
|
||||
"""Whether a model may capture its dedicated talker MTP graph."""
|
||||
return True
|
||||
|
||||
@classmethod
|
||||
def has_flash_attn_package(cls) -> bool:
|
||||
"""Check if a Flash Attention package is available and usable on this platform."""
|
||||
|
||||
Reference in new issue
Block a user