[AMD] Fix MiniMax M3 state transfer in Mori PD (#29756)
Co-authored-by: Duyi-Wang <duyi.wang@amd.com>
This commit is contained in:
@@ -1092,7 +1092,7 @@ class MoriKVManager(CommonKVManager):
|
|||||||
dst_dims,
|
dst_dims,
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
elif st in ("swa", "dsa", "swa_ring", "c128_state"):
|
elif st in ("swa", "dsa", "swa_ring", "c128_state", "minimax_index_k"):
|
||||||
statuses.extend(
|
statuses.extend(
|
||||||
self._send_swa_dsa_state(
|
self._send_swa_dsa_state(
|
||||||
peer_info,
|
peer_info,
|
||||||
@@ -1219,6 +1219,15 @@ class MoriKVManager(CommonKVManager):
|
|||||||
f"PD state transfer does not support TP-mismatched non-MLA SWA models "
|
f"PD state transfer does not support TP-mismatched non-MLA SWA models "
|
||||||
f"(prefill_tp_size={self.attn_tp_size}, decode_tp_size={peer_info.decode_tp_size})"
|
f"(prefill_tp_size={self.attn_tp_size}, decode_tp_size={peer_info.decode_tp_size})"
|
||||||
)
|
)
|
||||||
|
if state_type == "minimax_index_k":
|
||||||
|
if self.pp_size is not None and self.pp_size > 1:
|
||||||
|
raise RuntimeError(
|
||||||
|
"PD disagg: PP>1 not supported for MiniMax sparse index yet."
|
||||||
|
)
|
||||||
|
if peer_info.decode_tp_size != self.attn_tp_size:
|
||||||
|
raise RuntimeError(
|
||||||
|
"PD disagg: heterogeneous TP not supported for MiniMax sparse index yet."
|
||||||
|
)
|
||||||
|
|
||||||
common_len = min(src_state_indices.size, dst_state_indices.size)
|
common_len = min(src_state_indices.size, dst_state_indices.size)
|
||||||
if (
|
if (
|
||||||
|
|||||||
Reference in New Issue
Block a user