GoldPancake
e7fa57ebae
Extract eh_proj Layer from ParallelLMHead for MTP to Avoid Weight Transposition Issue ( #2707 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* fix mtp eh_proj layer
* fix mtp update_cfg function
* fix stringdoc
* simplify class name
2025-07-04 14:15:04 +08:00
gaoziyuan
a5ae88ded9
[feature]add fd whl version info ( #2698 )
2025-07-04 14:12:42 +08:00
ltd0924
87e638498c
[RL] update reschedule finish reason ( #2709 )
2025-07-04 13:47:36 +08:00
freeliuzc
667547be59
support chunk_prefill in MTP ( #2705 )
2025-07-04 11:55:48 +08:00
Yuanle Liu
240bdac2a4
[feat] support fa3 backend for pd disaggregated ( #2695 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* support fa3 backend run in pd disaggregated
* support fa3 backend run in pd disaggregated
* support fa3 backend run in pd disaggregated
* support fa3 backend run in pd disaggregated
* delete use_fast_ffn
2025-07-03 22:33:27 +08:00
ltd0924
00863c43fd
[Bug] fix logger format ( #2689 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-03 19:58:03 +08:00
Jiang-Jia-Jun
9fd74f75bd
Update dynamic_weight_manager.py
2025-07-03 15:55:22 +08:00
Jiang-Jia-Jun
05c670e593
[Sync] Update to latest code ( #2679 )
...
* [Sync] Update to latest code
* Add new code files
* Add new code files
* update code
* Try to fix build.sh
* Try to fix build.sh
* Update code
* Update requirements.txt
* Update code
---------
Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com >
2025-07-03 15:43:53 +08:00
AIbin
a197dcd729
【Inference Optimize】Support ERNIE-4_5-300B-A47B-2BITS-Paddle model TP2/TP4 Inference ( #2666 )
...
* Support TP2&TP4 Wint
* Support TP2&TP4 Wint2 Inference
2025-07-01 18:29:11 +08:00
ltd0924
50aa4080c0
[Serving] fix offline inference sampling parameters overwrite ( #2654 )
2025-07-01 10:17:46 +08:00
Jiang-Jia-Jun
92c2cfa2e7
Sync v2.0 version of code to github repo
2025-06-29 23:29:37 +00:00
jiangjiajun
fb18f3092d
[LLM] Add output module and polish docs
2025-06-09 20:26:53 +08:00
jiangjiajun
684703fd72
[LLM] First commit the llm deployment code
2025-06-09 19:20:15 +08:00
Zheng-Bicheng
9faf1b5ad9
Merge branch 'PaddlePaddle:develop' into develop
2025-02-12 21:23:36 +08:00
Jiang-Jia-Jun
d4bbdbefea
Merge pull request #2559 from MaaXYZ/fix/build_error
...
fix: build error without ENABLE_PADDLE2ONNX
2025-01-10 13:55:49 +08:00
Jiang-Jia-Jun
618826b39d
Merge pull request #2560 from MaaXYZ/perf/read_file
...
perf: ReadBinaryFromFile supports Chinese path
2025-01-10 13:55:27 +08:00
Jiang-Jia-Jun
17d204b975
Merge pull request #2561 from MaaXYZ/feat/directml
...
feat: select adapter id for DirectML
2025-01-10 13:54:44 +08:00
MistEO
ec3d4c714c
fix: valid_directml_backends
2024-11-21 16:47:16 +08:00
MistEO
11214a642f
fix: typo of log
2024-11-21 16:11:31 +08:00
MistEO
227cc37a7b
fix: config including
2024-11-21 16:02:19 +08:00
MistEO
2507a172f8
feat: select adapter id for DirectML
2024-11-20 14:38:32 +08:00
MistEO
e321ae55a1
fix: windows build error
2024-11-20 00:27:27 +08:00
MistEO
5662fa3903
fix: build error for CI
2024-11-19 19:16:16 +08:00
MistEO
1bbba6fbe3
fix: build error on old C++ std
2024-11-19 19:12:17 +08:00
MistEO
f5ccf62fda
perf: ReadBinaryFromFile supports Chinese path
2024-11-19 19:04:19 +08:00
MistEO
eca2ae8b94
fix: build error without ENABLE_PADDLE2ONNX
2024-11-19 16:37:46 +08:00
Zheng-Bicheng
527536565a
Update cosine_similarity.cc
2024-11-07 16:41:03 +08:00
ChaoII
0ae0dc9d82
[BUG FIX] fix memory leak for ort backend
2024-03-29 09:00:05 +08:00
ChaoII
cc8d1f3c9f
[BUG FIX] add export declaration of GaussianRandom function ( #2379 )
...
* Update fd_type.cc
[bug fix]add define for destroy TwoDimArrayCstr for c_api
* [BUG FIX] add export declaration of GaussianRandom function
2024-03-05 13:37:20 +08:00
Albin
1314f3267e
bug fix: 修复contrib中的det模型后处理在遇到没有检测框的图时导致同batch中接下来的图片结果全部为空的bug ( #2378 )
2024-02-27 19:21:17 +08:00
ThinkWD
cfd80e95a1
修复 #2359 ( #2363 )
...
Update pptinypose_utils.cc
添加 py 范围限制, 避免 utils::DarkParse 内部出现数组越界
2024-01-29 19:16:19 +08:00
DefTruth
cfebd24dfc
[Backend] fix ort backend windows build error ( #2269 )
...
* support ort offline graph optimize option
* support ort offline graph optimize option
* [Backend] fix windows build error
2023-11-02 12:51:46 +08:00
DefTruth
6a8cd4d759
[Backend] support ort offline graph optimize option ( #2268 )
...
* support ort offline graph optimize option
* support ort offline graph optimize option
2023-11-02 09:19:33 +08:00
Jason
d910d6116c
[Model] Fix nms problem ( #2230 )
...
fix nms problem
2023-10-10 16:24:33 +08:00
ChaoII
771dcf4b91
[Backend]Update sophgo_backend.cc for FP16 data type ( #2161 )
2023-08-16 14:12:58 +08:00
DefTruth
ade27d29cb
[Sync][Internal] sync some internal features of paddle3d inference ( #2118 )
...
* [Sync][Internal] sync some internal codes
* [Sync][Internal] sync some internal features of paddle3d inference
* [Sync][Internal] sync some internal features of paddle3d inference
2023-07-17 23:06:51 +08:00
DefTruth
681ccc4c24
[Sync][Internal] sync some internal paddle3d codes ( #2108 )
2023-07-13 22:06:28 +08:00
DefTruth
d5ad3d9c8d
[Bug Fix] fixed paddle custom ops windows build error ( #2103 )
...
* [cmake] upgrade windows paddle inference -> 2.5.0
* [cmake] upgrade windows paddle inference -> 2.5.0
* fix paddle custom ops bug on windows
* [Backend] refactor paddle custom ops
* [Bug Fix] fixed paddle custom ops windows build error
2023-07-13 14:04:01 +08:00
DefTruth
99c2b6592d
[Backend] refactor paddle custom ops -> fastdeploy::paddle_custom_ops ( #2101 )
...
* [cmake] upgrade windows paddle inference -> 2.5.0
* [cmake] upgrade windows paddle inference -> 2.5.0
* fix paddle custom ops bug on windows
* [Backend] refactor paddle custom ops
2023-07-13 09:00:03 +08:00
DefTruth
2542a75b61
[cmake] upgrade windows paddle inference -> 2.5.0 ( #2100 )
...
* [cmake] upgrade windows paddle inference -> 2.5.0
* [cmake] upgrade windows paddle inference -> 2.5.0
* fix paddle custom ops bug on windows
2023-07-12 18:39:06 +08:00
zengshao0622
c95fc1fba8
[Bug Fix] fix centerpoint malloc bug ( #2099 )
2023-07-12 17:17:22 +08:00
DefTruth
cf1ff2077d
[Bug Fix] fix trt backend page-locked error ( #2095 )
...
* [Bug Fix] fix trt backend page-locked error
* Update trt_backend.cc
2023-07-11 13:49:47 +08:00
DefTruth
4c1e80b723
[Bug Fix] fixed ocr visualize error ( #2090 )
2023-07-07 17:43:08 +08:00
yeliang2258
ad1f46f7d9
Add ORT fp16 support in server ( #2069 )
...
* add ort fp16 support in server
* update paddle2onnx url
* update ort fp16 api
* add disable_ort_fp16_op_types in serving
2023-07-05 17:50:00 +08:00
zengshao0622
79a3587339
[Model] Add Paddle3D CenterPoint model ( #2078 )
...
* add centerpoint
* update for review comments
2023-07-03 13:39:16 +08:00
DefTruth
b2426aefa9
[Backend] add paddle custom ops compatible policy ( #2070 )
...
* Add centerpoint
* fix postprocess op file name
* [Backend] add paddle custom ops compatible policy
* [Backend] add paddle custom ops compatible policy
* [Backend] add paddle custom ops compatible policy
* upgrade linx paddle gpu -> 2.5
* add custom op compatible policy for paddle 2.5
* add custom op compatible policy for paddle 2.5
* add custom op compatible policy for paddle 2.5
* add collect_trt_shape_by_device option for paddle backend
* add collect_trt_shape_by_device option for paddle backend
* add custom op option for python build
* fix python build bugs
* update paddle linux x86 cpu only lib
* update paddle linux gpu lib
* update patchelf cmake
* fix paddle backend option pybind
* update paddle_inference.cmake
* add cuda sm_80 support (A100)
---------
Co-authored-by: zengshao0622 <peter_z96@163.com >
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-29 22:32:14 +08:00
JugendTraum
4c3e7030e1
Update rknpu2_backend.cc ( #2064 )
...
Update rknpu2_backend.cc Signed-off-by: JugendTraum <443248173@qq.com >
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-06-26 04:58:12 -07:00
zengshao0622
709ba51612
[WIP]Add VI-LayoutXLM ( #2048 )
...
* WIP, add VI-LayoutXLM
* fix pybind
* update the dir of ser_vi_layoutxlm model
* update dir and name of ser_vi_layoutxlm model
* update model name to StructureV2SerViLayoutXLMModel
* fix import paddle bug
---------
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com >
2023-06-26 16:40:05 +08:00
DefTruth
dea3795930
[Backend] Add backward compatible for paddle inference 2.4.x ( #2062 )
...
* [Backend] Add backward compatiable for paddle infernence 2.4.x
* [Backend] Add backward compatiable for paddle infernence 2.4.x
2023-06-25 19:27:36 +08:00
DefTruth
ba8649a69d
[Model] update PP-ShiTuV2-rec preprocess parser policy ( #2061 )
...
* [benchmark] fixed paddlex benchmark for picodet 320
* [Bug Fix] fixed paddlex ppseg pp-trt infer error
* [Bug Fix] fixed paddlex dino benchmark trt shapes
* [benchmark] support paddlex ppyoloe pptrt benchmark
* [benchmark] adjust paddlex dino trt shapes
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add max_workspace_size flags for tensorrt/pptrt backend
* [benchmark] add ort/paddle h2d gpu configs for paddlex
* [benchmark] update paddlex benchmark scripts
* [benchmark] update paddlex benchmark scripts
* [Model] update PP-ShituV2-rec preprocess parser policy
---------
Co-authored-by: qiuyanjun <qiuyanjun@baidu.com >
2023-06-25 13:50:02 +08:00
