apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Revert "[Bug Fix] fix ernie4_5_vl_moe (#4843)" (#4863)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
Details
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
Details
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
Details
CE Compile Job / Show Code Archive Output (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
Details
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
Details
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Details
Deploy GitHub Pages / deploy (push) Has been cancelled
Details
Publish Job / publish_pre_check (push) Has been cancelled
Details
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Details
Publish Job / FD-Clone-Linux (push) Has been cancelled
Details
Publish Job / Show Code Archive Output (push) Has been cancelled
Details
Publish Job / BUILD_SM8090 (push) Has been cancelled
Details
Publish Job / BUILD_SM8689 (push) Has been cancelled
Details
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Details
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Details
Publish Job / Run FD Image Build (push) Has been cancelled
Details
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Details
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Details
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Details
Publish Job / Run Base Tests (push) Has been cancelled
Details
Publish Job / Run Accuracy Tests (push) Has been cancelled
Details
Publish Job / Run Stable Tests (push) Has been cancelled
Details
CI Images Build / FD-Clone-Linux (push) Has been cancelled
Details
CI Images Build / Show Code Archive Output (push) Has been cancelled
Details
CI Images Build / CI Images Build (push) Has been cancelled
Details
CI Images Build / BUILD_SM8090 (push) Has been cancelled
Details
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Details
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
Details
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Details
CI Images Build / Run Base Tests (push) Has been cancelled
Details
CI Images Build / Run Accuracy Tests (push) Has been cancelled
Details
CI Images Build / Run Stable Tests (push) Has been cancelled
Details
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
Details

Browse Source 
This reverts commit 6460d4df27.
This commit is contained in:
Jiang-Jia-Jun
2025-11-06 19:18:29 +08:00
committed by GitHub
parent 6460d4df27
commit 6b68c58e8d
1 changed files with 2 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
fastdeploy/model_executor/models/ernie4_5_vl/ernie4_5_vl_moe.py
View File

@@ -72,7 +72,6 @@ class VLMoEMeta:
image_index: paddle.Tensor
token_type_ids: paddle.Tensor
image_token_num: paddle.Tensor
num_image_patch_id: paddle.Tensor
def __str__(self):
return (
@@ -500,13 +499,11 @@ class Ernie4_5_VLModel(nn.Layer):
ids_remove_padding: paddle.Tensor,
) -> VLMoEMeta:
image_mask = ids_remove_padding >= self.im_patch_id
image_mask = ids_remove_padding == self.im_patch_id
token_type_ids = image_mask.cast("int32")
image_token_num = image_mask.sum()
token_num = ids_remove_padding.shape[0]
text_token_num = paddle.maximum((token_num - image_token_num), paddle.ones([], dtype="int64"))
num_image_patch_id = ids_remove_padding == self.im_patch_id
num_image_patch_id = num_image_patch_id.cast("int32").sum()
# The scenario requiring padding is CUDA graph, thus we only need to pad the maximum capture size.
self._cuda_graph_buffers["token_type_ids"][: self.fd_config.graph_opt_config.max_capture_size].fill_(-1)
@@ -520,7 +517,6 @@ class Ernie4_5_VLModel(nn.Layer):
image_index=self._cuda_graph_buffers["image_index"][:token_num],
token_type_ids=self._cuda_graph_buffers["token_type_ids"][:token_num],
image_token_num=self._cuda_graph_buffers["image_token_num"],
num_image_patch_id=num_image_patch_id,
)
def get_input_embeddings(self, ids_remove_padding: paddle.Tensor) -> paddle.Tensor:
@@ -791,7 +787,7 @@ class Ernie4_5_VLMoeForConditionalGeneration(ModelForCasualLM):
input_embeddings = self.get_input_embeddings(
ids_remove_padding=ids_remove_padding,
image_features=image_features,
image_token_num=vl_moe_meta.num_image_patch_id.item(),
image_token_num=vl_moe_meta.image_token_num.item(),
)
self._input_embeddings.copy_(input_embeddings, False)