[Core] [Bugfix] Add Input Embeddings (#15428)
Signed-off-by: Andrew Sansom <andrew@protopia.ai> Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Co-authored-by: 临景 <linjing.yx@alibaba-inc.com> Co-authored-by: Bryce1010 <bryceyx@gmail.com> Co-authored-by: Nan2018 <nan@protopia.ai> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com> Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
co-authored by
临景
Bryce1010
Nan2018
Cyrus Leung
DarkLight1337
parent
9e2de9b9e9
commit
cc2a77d7f1
@@ -367,9 +367,17 @@ class FlashInferState(AttentionState):
|
||||
# scheduled while CUDA graph mode is enabled. We don't run graph in that
|
||||
# case.
|
||||
if use_cuda_graph and is_decode:
|
||||
batch_size = model_input.input_tokens.shape[0]
|
||||
state = (self.runner.graph_runners[model_input.virtual_engine]
|
||||
[batch_size].attn_state)
|
||||
if model_input.inputs_embeds is None:
|
||||
batch_size = model_input.input_tokens.shape[0]
|
||||
state = (
|
||||
self.runner.graph_runners[model_input.virtual_engine][(
|
||||
batch_size, False)].attn_state)
|
||||
else:
|
||||
batch_size = model_input.inputs_embeds.shape[0]
|
||||
state = (
|
||||
self.runner.graph_runners[model_input.virtual_engine][(
|
||||
batch_size, True)].attn_state)
|
||||
|
||||
model_input.attn_metadata.prefill_wrapper = state._get_prefill_wrapper(
|
||||
)
|
||||
model_input.attn_metadata.decode_wrapper = state._get_decode_wrapper()
|
||||
|
||||
Reference in New Issue
Block a user