Commit Graph

1243 Commits

Author SHA1 Message Date
YuBaoku
819b2dbbae Revert "【New Feature】W4afp8 supports per group quantization (#4272)" (#4854)
This reverts commit 93fcf7e4ec.
2025-11-06 17:48:28 +08:00
zhupengyang
b54eb7ad81 [XPU] ep+tp all2all (#4836) 2025-11-06 17:26:14 +08:00
Echo-Nie
c18b177f21 fix the get_act_fn,_load_st_projector (#4824) 2025-11-06 16:13:35 +08:00
Echo-Nie
e4f1267186 bug: fix list to List (#4818) 2025-11-06 16:13:12 +08:00
Juncai
08ca0f6aea [Feature] [PD] add simple router and refine splitwise deployment (#4709)
* add simple router and refine splitwise deployment

* fix
2025-11-06 14:56:02 +08:00
Ayakouji
831266da7a [Fix] fix ernie4_5_vl model torch format loadding (#4447)
* fix

* add test

* fix test

* fix test

* update
2025-11-06 14:34:21 +08:00
kxz2002
5bdd40da5d [BugFix] Fix ernie_vl_reasoning_parsers.py 'end_token' to 'think_end_token' (#4805)
* fix ernie_vl_reasoning_parsers.py 'end_token' to 'think_end_token'

* add unit tests
2025-11-06 11:28:55 +08:00
周周周
69fa741763 remove seq_lens_this_time (#4821) 2025-11-06 11:06:28 +08:00
K11OntheBoat
62dfad4a5f [PD Disaggregation] Support Qwen3-MoE use PD + EP inference. (#4691)
support Qwen-MoE PD/EP
2025-11-06 10:32:15 +08:00
yangjianfengo1
93fcf7e4ec 【New Feature】W4afp8 supports per group quantization (#4272)
* w4afp8 支持per group

* code style

* 精度完成

* revert append attn utils

* ffn1 动态量化

* ffn2 支持动态量化

* code style

* code style

* 修改单测

* 修改单测

* fix bug

* Implement conditional parameter creation for layers

Add parameter creation for up_gate_proj_in_scale when ep_size > 1.

* code style

* fix conflict

* code style

* code style

* 修复w4aint8 精度

* fix ci

---------

Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com>
2025-11-05 21:00:23 +08:00
李泳桦
fcd2f05dff [BugFix] fix messages being inplace modified in offline chat api (#4831) 2025-11-05 20:46:33 +08:00
ApplEOFDiscord
131d76dd64 [Bug Fix] process transparent image (#4807)
* process transparent image

* english comments

* process transparency at downloading

* fix

* remove useless codes
2025-11-05 17:15:24 +08:00
yinwei
ea1dd0e735 [XPU]Support V1 loader in weight_only Model (#4808)
* support v1 loader in wint8

* code style

* update

---------

Co-authored-by: root <root@gajl-bbc-onlinec-com-1498356.gajl.baidu.com>
2025-11-05 17:09:11 +08:00
chenjian
cc8f5312f5 [Feature] Add timestamp for profiler (#4726)
* [Feature] Add timestamp for profiler

* fix bug for offine inference

* fix for ci

* fix

* fix ci
2025-11-05 12:04:59 +08:00
周周周
876e4a8935 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
2025-11-05 11:55:51 +08:00
kxz2002
9676cc87d6 fix parser register name (#4795)
Co-authored-by: luukunn <83932082+luukunn@users.noreply.github.com>
2025-11-05 11:27:30 +08:00
zhupengyang
2fd254e5b7 support ep+tp at op layer (#4688) 2025-11-05 11:15:57 +08:00
周周周
937eb3c6ed [get_padding_offset.] clean get_padding_offset.cu (#4777)
[get_padding_offset.] clean get_padding_offset.cu (#4777)
2025-11-05 10:47:40 +08:00
chen
1c3ca48128 [Feature][Executor] GPU Model Runner Supports prompt_logprobs and max_logprobs (#4769) 2025-11-05 10:43:25 +08:00
xiaozude
74722308f2 [Metax] adapt cutlass moe and fix mla attention (#4602)
Co-authored-by: Yuanle Liu <yuanlehome@163.com>
2025-11-05 10:03:49 +08:00
Haonan Luo
2c281e617c Update Unit Test for PaddleOCR-VL (#4802)
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
* fix paddleocr prefix cache bug

* add test for paddleocr_vl

* disable prefix-caching in ocr

* add test for paddleocr_vl

* Fix top_p for rejection sampling

* add test for ocr processor; fix top_p for rejection sampling

* add test for ocr processor; fix top_p for rejection sampling

* add test for ocr processor; fix top_p for rejection sampling

* add test for ocr processor; fix top_p for rejection sampling

* add test for ocr processor; fix top_p for rejection sampling

---------

Co-authored-by: ming1753 <ideaminghp@163.com>
Co-authored-by: ming1753 <61511741+ming1753@users.noreply.github.com>
2025-11-04 22:40:15 +08:00
李泳桦
1b61d62ecf [fix] fix v0 pd, let worker step_shm_value create=False (#4780) 2025-11-04 20:37:57 +08:00
lzy
3e9dda39ab supports pd partn (#4615)
* supports pd partn

* fix codestype
2025-11-04 16:36:35 +08:00
lzy
af7e0f27f3 supports internode_ll_two_stage (#4162)
* supports internode_ll_two_stage

* supports internode_ll_two_stage

* supports internode_ll_two_stage

* supports internode_ll_two_stage

* supports D internode_ll_two_stage

* fix codestype

* fix xpu internode_ll_two_stage

* fix xpu internode_ll_two_stage
2025-11-04 16:35:40 +08:00
kxz2002
8a40374bfe [BugFix] Fix ernie4_5_vl_processor.py and qwen_vl_processor.py can not disable thinking (#4762)
* fix ernie4_5_vl_processor.py and qwen_vl_processor.py

* add unit test
2025-11-04 16:00:32 +08:00
ddchenhao66
bffa08b74b [XPU] fix thinking bug where output only contains reasoning_content (#4761)
Co-authored-by: ddchenhao66 <dhaochen163.com>
2025-11-04 14:32:35 +08:00
freeliuzc
855a2a609a fix attn_params (#4787) 2025-11-04 13:01:38 +08:00
kevin
5233825562 test scheduler (#4739) 2025-11-03 20:12:14 +08:00
Yuan Xiaolan
8690cf8569 fix Cfp8 for RL load (#4144)
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
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FD Image Build (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Run Accuracy Tests (push) Has been cancelled
CI Images Build / Run Stable Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
2025-11-03 17:51:51 +08:00
Neil Zhu
c95d0740ec [Metax] adapt cutlass moe for ernie-vl (#4685) 2025-11-03 17:44:27 +08:00
chenjian
25498efcf3 [Optimize] Support and robust for tpN for PD (#4595)
* [Optimize] Support and robust for tpN for PD

* fix

* fix

* support dpM tpN for cache messager

* fix

* fix token counter

* fix bug for merge develop

* fix bug

* robust cache messager for v0
2025-11-03 15:38:31 +08:00
luukunn
7b35488779 【DataProcessor】add options thinking_mode (#4735)
* add thinking_mode

* add thinking_mode

* add thinking_mode

* add thinking_mode

* add thinking_mode

* add thinking_mode

* add unit test
2025-11-03 14:30:07 +08:00
yinwei
377f3bf5f2 [XPU] add v1 support for bf16 (#4744)
* support v1 loader

* update code style

* update code
2025-11-03 14:13:17 +08:00
chenjian
f83d0cf127 [Feature] Support eplb for fd (#4599)
* support eplb

* support eplb

---------

Co-authored-by: kevin <chengyf112@gmail.com>
2025-11-03 14:08:15 +08:00
freeliuzc
11398790d3 [Speculative Decoding][MTP]Support attn mask offset (#4641)
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
* [MTP]Merge support attn (#4591)

* support mask_offset in speculate decoding

* fix dummpy run output

* add unit test

* fix unit test import

* support attn_mask_offset in mtp mode

* add update_attn_mask op

* fix unit test && fix code-style
2025-11-03 10:08:01 +08:00
freeliuzc
f44f4bafd1 support mtp in splitewise and scheduler_v1 mode (#4743) 2025-11-03 10:07:15 +08:00
lizexu123
4ac6de9a3c [Feature] support pooling model runner (#4590)
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
* support qwen3-embedding

* support qwen3-embedding-0.6b

* fix

* fix bug

* fix test_return_token_ids.py and update enable_thinking

* fix mtp dummy_run

* merge develop

* fix np.float32

* delete FD_DISABLE_CHUNKED_PREFILL and FD_USE_GET_SAVE_OUTPUT_V1

* delete and build_stream_transfer_data

* fix test_update_v1:

* fix

* fix

* update dummy_run post_process

* delete test_update_v1

* fix

* fix dummy_run

* fix model_path

* fix model_path

* fix dummy_run
2025-10-31 22:32:05 +08:00
Yuanle Liu
b301bd6c31 [BugFix] fix thinking bug (#4710)
* fix thinking bug

* fix ut

* update

* fix
2025-10-31 22:00:31 +08:00
ddchenhao66
3cbca75cc8 [XPU] xpu support neox style ROPE (#4719)
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
Publish Job / publish_pre_check (push) Has been cancelled
Publish Job / print_publish_pre_check_outputs (push) Has been cancelled
Publish Job / FD-Clone-Linux (push) Has been cancelled
Publish Job / Show Code Archive Output (push) Has been cancelled
Publish Job / BUILD_SM8090 (push) Has been cancelled
Publish Job / BUILD_SM8689 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8090 (push) Has been cancelled
Publish Job / PADDLE_PYPI_UPLOAD_8689 (push) Has been cancelled
Publish Job / Run FD Image Build (push) Has been cancelled
Publish Job / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
Publish Job / Run FastDeploy LogProb Tests (push) Has been cancelled
Publish Job / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
Publish Job / Run Base Tests (push) Has been cancelled
Publish Job / Run Accuracy Tests (push) Has been cancelled
Publish Job / Run Stable Tests (push) Has been cancelled
CI Images Build / FD-Clone-Linux (push) Has been cancelled
CI Images Build / Show Code Archive Output (push) Has been cancelled
CI Images Build / CI Images Build (push) Has been cancelled
CI Images Build / BUILD_SM8090 (push) Has been cancelled
CI Images Build / Run FastDeploy Unit Tests and Coverage (push) Has been cancelled
CI Images Build / Run FastDeploy LogProb Tests (push) Has been cancelled
CI Images Build / Extracted partial CE model tasks to run in CI. (push) Has been cancelled
CI Images Build / Run Base Tests (push) Has been cancelled
CI Images Build / Run Accuracy Tests (push) Has been cancelled
CI Images Build / Run Stable Tests (push) Has been cancelled
CI Images Build / Publish Docker Images Pre Check (push) Has been cancelled
Co-authored-by: ddchenhao66 <dhaochen163.com>
2025-10-31 18:14:25 +08:00
Jundong Liu
88a94c821b [FDConfig] [PD Disaggregation] [Graph Optimization] Close Cudagraph for P node when PD Disaggregation (#4632)
* Close cudagraph for P node when PD Disaggregation

* fix problem
2025-10-31 16:44:25 +08:00
AIbin
316f784016 fix wint2 config (#4721) 2025-10-31 15:44:14 +08:00
kevin
c801d31c9c add checker (#4711) 2025-10-31 15:26:35 +08:00
kevin
096d87d335 fix bug (#4679) 2025-10-31 14:59:18 +08:00
李泳桦
0f75b62de2 [BugFix] Fix profile run in pd-disaggregated deployment (#4584)
* [fix] fix pd+dp+ep bug

* [fix] fix again

* [ci] fix code style
2025-10-31 14:42:00 +08:00
kevin
64e875b460 [Scheduler] update v1 prefill batch (#4611)
* update v1 prefill batch

* update code

* update code
2025-10-31 14:03:01 +08:00
Sunny-bot1
9b18f0b55d cache scale load (#4624) 2025-10-31 11:58:33 +08:00
GoldPancake
1f3ce65b58 [Feature] support mtp distribution equivalence verification (#4699)
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
2025-10-31 11:45:04 +08:00
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
kxz2002
a2870ed4a9 [Feature] Unify the registration name recognition for tool_parser and reasoning_parser to “-” (#4668)
* parser register name unify

* change ernie_x1 to ernie-x1

* change ernie4_5_vl to ernie-45-vl

* fix unit test
2025-10-31 10:45:27 +08:00
kxz2002
82bd7e5db4 [BugFix] Fix finish reason in _create_chat_completion_choice (#4582)
* fix n_param _create_chat_completion_choicel

* fix unit test

* fix final_res

* modify unit tests
2025-10-31 10:42:19 +08:00