mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2026-04-23 00:17:25 +08:00
[Feature]Support tag phase token enforce generation (#6034)
* support tag phase token enforce generation * optimize note and some feature * fix sampler unit test --------- Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
This commit is contained in:
@@ -310,6 +310,7 @@ elif paddle.is_compiled_with_cuda():
|
||||
"gpu_ops/update_attn_mask_offsets.cu",
|
||||
"gpu_ops/fused_neox_rope_embedding.cu",
|
||||
"gpu_ops/gelu_tanh.cu",
|
||||
"gpu_ops/reasoning_phase_token_constraint.cu",
|
||||
]
|
||||
|
||||
# pd_disaggregation
|
||||
|
||||
Reference in New Issue
Block a user