mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
remove input_ids from ForwardMeta (#4793)
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
Some checks failed
CE Compile Job / ce_job_pre_check (push) Has been cancelled
CE Compile Job / print_ce_job_pre_check_outputs (push) Has been cancelled
CE Compile Job / FD-Clone-Linux (push) Has been cancelled
CE Compile Job / Show Code Archive Output (push) Has been cancelled
CE Compile Job / BUILD_SM8090 (push) Has been cancelled
CE Compile Job / BUILD_SM8689 (push) Has been cancelled
CE Compile Job / CE_UPLOAD (push) Has been cancelled
Deploy GitHub Pages / deploy (push) Has been cancelled
This commit is contained in:
@@ -30,6 +30,7 @@ class TOYGPUModelRunner:
|
||||
self.pre_max_block_num = 16
|
||||
# Not the tensor in real sense, just for make ForwardMeta
|
||||
self.share_inputs = {}
|
||||
|
||||
self.share_inputs["input_ids"] = paddle.full(
|
||||
[self.max_num_seqs, self.max_model_len],
|
||||
0,
|
||||
@@ -63,7 +64,6 @@ class TOYGPUModelRunner:
|
||||
"""
|
||||
# Ignore the attentionbackbend for simplify
|
||||
self.forward_meta = ForwardMeta(
|
||||
input_ids=self.share_inputs["input_ids"],
|
||||
ids_remove_padding=self.share_inputs["ids_remove_padding"],
|
||||
# rotary_embs=self.share_inputs["rope_emb"],# Ignore the rope_emb for simplify
|
||||
# attn_backend=self.attn_backends[0],# Ignore the attn_backbend for simplify
|
||||
|
||||
Reference in New Issue
Block a user