Ryan 28de91b50f [Graph Optimization] SOT+CUDAGraph support ERNIE4.5T VL 28B / 424B (#4645) ...

* 45TVL support sot+CUDAGraph

* mv unitest from ce_deploy 2 e2e

* add test_EB_VL_Lite_sot_serving

* rm useless line

* add openai_client

* fix unitest && reduce computing resources

2025-10-31 11:38:43 +08:00

..

ernie4_5_vl

[Graph Optimization] SOT+CUDAGraph support ERNIE4.5T VL 28B / 424B (#4645)

2025-10-31 11:38:43 +08:00

paddleocr_vl

[BugFix] PaddleOCR-VL fix FD_DEBUG type and support v1 loader (#4605)

2025-10-28 09:47:47 +08:00

qwen2_5_vl

[V1 loader] Qwen25 VL support v1 loader and torch style safetensors load (#4388)

2025-10-27 10:54:15 +08:00

__init__.py

[Feature] support pool (#3827)

2025-09-22 14:09:09 +08:00

adapters.py

[Feature] support pooling model dummy_run (#4345)

2025-10-17 13:30:55 +08:00

deepseek_v3.py

[Metax] adapt DeepSeek (#4498)

2025-10-24 10:14:53 +08:00

ernie4_5_moe.py

register_model_class compatible with plugins (#4236)

2025-09-24 11:17:12 +08:00

ernie4_5_mtp.py

[Executor]CUDAGraph support Speculate Decode (#3769)

2025-10-09 21:18:29 +08:00

ernie_vl_rm.py

add qwen-2.5-7B-PRM/ernie-rm (#4319)

2025-10-20 15:31:03 +08:00

glm4_moe.py

[BugFix]Dev fix custom ar unstable result (#4437)

2025-10-17 11:47:16 +08:00

gpt_oss.py

Support GPT-OSS-BF16 (#4240)

2025-10-20 14:44:58 +08:00

interfaces_base.py

Optimizing the performance of think length limit using custom operators (#4279)

2025-10-20 21:09:13 +08:00

model_base.py

Optimizing the performance of think length limit using custom operators (#4279)

2025-10-20 21:09:13 +08:00

qwen2_rm.py

add qwen-2.5-7B-PRM/ernie-rm (#4319)

2025-10-20 15:31:03 +08:00

qwen2.py

add qwen-2.5-7B-PRM/ernie-rm (#4319)

2025-10-20 15:31:03 +08:00

qwen3.py

[Feature] support pooling model dummy_run (#4345)

2025-10-17 13:30:55 +08:00

qwen3moe.py

register_model_class compatible with plugins (#4236)

2025-09-24 11:17:12 +08:00

tp_utils.py

Supports DP+TP+EP hybrid parallel deployment strategy (#3489)

2025-08-26 00:04:01 -07:00

utils.py

delete useless code (#4544)

2025-10-23 13:40:34 +08:00