apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-23 00:17:25 +08:00
Code Issues Actions 19 Packages Projects Releases Wiki Activity

[Iluvatar GPU] Adapt VL model (#4313)

Browse Source
This commit is contained in:
yzwu
2025-10-17 16:13:38 +08:00
committed by GitHub
parent ba5c2b7e37
commit 4b661512ca
15 changed files with 345 additions and 228 deletions
Download Patch File Download Diff File Expand all files Collapse all files
custom_ops/setup_ops.py
+3 -2
View File
@@ -290,7 +290,6 @@ elif paddle.is_compiled_with_cuda():
"gpu_ops/cpp_extensions.cc",
"gpu_ops/share_external_data.cu",
"gpu_ops/per_token_quant_fp8.cu",
"gpu_ops/extract_text_token_output.cu",
"gpu_ops/update_split_fuse_input.cu",
"gpu_ops/text_image_index_out.cu",
"gpu_ops/text_image_gather_scatter.cu",
@@ -538,6 +537,9 @@ elif paddle.is_compiled_with_custom_device("iluvatar_gpu"):
"gpu_ops/token_penalty_multi_scores.cu",
"gpu_ops/sample_kernels/rejection_top_p_sampling.cu",
"gpu_ops/sample_kernels/top_k_renorm_probs.cu",
"gpu_ops/text_image_index_out.cu",
"gpu_ops/text_image_gather_scatter.cu",
"gpu_ops/set_data_ipc.cu",
"iluvatar_ops/moe_dispatch.cu",
"iluvatar_ops/moe_reduce.cu",
"iluvatar_ops/paged_attn.cu",
@@ -596,7 +598,6 @@ elif paddle.device.is_compiled_with_custom_device("metax_gpu"):
"gpu_ops/read_data_ipc.cu",
"gpu_ops/dequant_int8.cu",
"gpu_ops/share_external_data.cu",
"gpu_ops/extract_text_token_output.cu",
"gpu_ops/moe/tritonmoe_preprocess.cu",
"gpu_ops/moe/moe_topk_select.cu",
"gpu_ops/recover_decode_task.cu",