apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 08:16:42 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Code Simplification] remove cum_offsets (#3410)
Some checks failed
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 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

Browse Source
This commit is contained in:
lizexu123
2025-08-18 20:21:25 +08:00
committed by GitHub
parent 2cf96ddd68
commit 32b39620bc
9 changed files with 73 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
fastdeploy/worker/gcu_model_runner.py
View File

@@ -423,7 +423,7 @@ class GCUModelRunner(ModelRunnerBase):
0,
dtype="int64",
)
self.share_inputs["cum_offsets"] = paddle.full([max_num_seqs, 1], 0, dtype="int32")
self.share_inputs["batch_id_per_token"] = paddle.full([max_num_seqs, 1], 0, dtype="int32")
self.share_inputs["cu_seqlens_q"] = paddle.full([max_num_seqs, 1], 0, dtype="int32")
self.share_inputs["cu_seqlens_k"] = paddle.full([max_num_seqs, 1], 0, dtype="int32")
@@ -522,7 +522,6 @@ class GCUModelRunner(ModelRunnerBase):
)
self.share_inputs["ids_remove_padding"].copy_(ids_remove_padding, False)
self.share_inputs["cum_offsets"].copy_(cum_offsets, False)
self.share_inputs["batch_id_per_token"].copy_(batch_id_per_token, False)
self.share_inputs["cu_seqlens_q"].copy_(cu_seqlens_q, False)
self.share_inputs["cu_seqlens_k"].copy_(cu_seqlens_k, False)
@@ -742,7 +741,7 @@ class GCUModelRunner(ModelRunnerBase):
hidden_states = rebuild_padding(
model_output,
self.share_inputs["cum_offsets"],
self.share_inputs["cu_seqlens_q"],
self.share_inputs["seq_lens_this_time"],
self.share_inputs["seq_lens_decoder"],
self.share_inputs["seq_lens_encoder"],
@@ -967,7 +966,7 @@ class GCUModelRunner(ModelRunnerBase):
hidden_states = rebuild_padding(
model_output,
self.share_inputs["cum_offsets"],
self.share_inputs["cu_seqlens_q"],
self.share_inputs["seq_lens_this_time"],
self.share_inputs["seq_lens_decoder"],
self.share_inputs["seq_lens_encoder"],