[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:
authored and GitHub committed 2026-08-11 17:19:09 +08:00
1 parent 4ab1b4ff9c
commit e04210d690
7 files changed
+125 -3

No files matched your search

+6 -2
View File
@@ -206,8 +206,12 @@ class OmniGPUModelRunner(GPUModelRunner):
cudagraph_mode = self.compilation_config.cudagraph_mode
assert cudagraph_mode is not None
has_separate_talker = getattr(self.model, "talker", None) is not None
talker_mtp_graph_safe = getattr(self.model, "talker_mtp_graph_safe", False)
if cudagraph_mode.has_full_cudagraphs() and (has_separate_talker or talker_mtp_graph_safe):
talker_mtp_graph_safe = getattr(self.model, "talker_mtp_graph_safe", None)
# Preserve the legacy separate-talker default only when the model has
# not declared graph safety. An explicit False must disable wrapping.
if talker_mtp_graph_safe is None:
talker_mtp_graph_safe = has_separate_talker
if cudagraph_mode.has_full_cudagraphs() and talker_mtp_graph_safe:
graph_wrapper_cls = current_omni_platform.get_graph_wrapper_cls()
self.talker_mtp = graph_wrapper_cls(talker_mtp, self.vllm_config, runtime_mode=CUDAGraphMode.FULL)
# TTS exposes mtp_hidden_size; Omni uses hf_text_config.hidden_size.