(Phase 1)Add ModelOpt FP8 auto-detect support for diffusion checkpoints #2709 (#2913)

Signed-off-by: roG0d <rodgarcas98@gmail.com>
Signed-off-by: roG0d <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Co-authored-by: roG0d <rodgarcas98@gmail.com>
This commit is contained in:
baonudesifeizhaiandroG0d authored and GitHub committed 2026-05-09 16:55:05 +08:00
1 parent 40a07e0d80
commit c4a0990044
26 files changed
+1214 -176

No files matched your search

@@ -132,7 +132,7 @@ class HunyuanModel(HunYuanModel):
# Params for weights, fp8 weight scales, fp8 activation scales
# (param_name, weight_name, expert_id, shard_id)
fused_moe_expert_mapping = fused_moe_make_expert_params_mapping(
self,
model=self,
ckpt_gate_proj_name="gate_proj",
ckpt_down_proj_name="down_proj",
ckpt_up_proj_name="up_proj",
@@ -416,10 +416,8 @@ class BailingMoeV2SparseMoeBlock(nn.Module):
dim=-1,
)
# FusedMoE expects 2D hidden_states.
hidden_states_2d = hidden_states.view(-1, h)
final_hidden_states = self.experts(hidden_states_2d, packed_routing)
final_hidden_states = final_hidden_states.view(bsz, seq_len, h)
return final_hidden_states.squeeze(0) if input_is_2d else final_hidden_states