[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:
Andrew Sansom
2025-05-02 01:06:39 -07:00
committed by GitHub
co-authored by 临景 Bryce1010 Nan2018 Cyrus Leung DarkLight1337
parent 9e2de9b9e9
commit cc2a77d7f1
22 changed files with 691 additions and 113 deletions
+11 -4
View File
@@ -84,10 +84,17 @@ class PoolingModelRunner(
# explore how to leverage it.
if (prefill_meta is None and decode_meta is not None
and decode_meta.use_cuda_graph):
assert model_input.input_tokens is not None
graph_batch_size = model_input.input_tokens.shape[0]
model_executable = self.graph_runners[virtual_engine][
graph_batch_size]
if model_input.inputs_embeds is None:
assert model_input.input_tokens is not None
graph_batch_size = model_input.input_tokens.shape[0]
model_executable = (
self.graph_runners[model_input.virtual_engine][(
graph_batch_size, False)])
else:
graph_batch_size = model_input.inputs_embeds.shape[0]
model_executable = (
self.graph_runners[model_input.virtual_engine][(
graph_batch_size, True)])
else:
model_executable = self.model