xiaolei373
5d131485d8
add error log to file ( #3431 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* feat(log):add_request_and_response_log
* feat[log]:add error log to file
2025-08-20 09:52:34 +08:00
kevin
67298cf4c0
add error traceback info ( #3419 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* add error traceback info
* update error msg
* update code
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-08-19 19:32:04 +08:00
Zero Rains
fef447e350
[V1 Loader] Support MOE parameters create and load for DeepGemm and marlin backend ( #3447 )
...
* support deepgemm backend
* support marlin backend
* remove print
* fix process_prequanted_weights
2025-08-19 14:15:53 +08:00
chen
6735626014
fix request_output sampling_params ( #3154 ) ( #3464 )
2025-08-19 13:52:50 +08:00
ltd0924
bca8905b40
[BugFix] fix control signal release failed ( #3390 )
...
* [BugFix] fix control signal release failed
* [BugFix] fix control signal release failed
* update
* update
* update
2025-08-19 13:51:38 +08:00
Zero Rains
8b12c80f90
[FixBug] compute early stopping with real batch size ( #3418 )
...
* [FixBug] compute early stopping with real batch size
* update
* fix test_sampler
2025-08-18 22:09:21 -07:00
luukunn
3a7a20d191
[Feature] Pass through the chat_template_kwargs to the data processing module ( #3421 )
...
* fix chat_template_args
* fix args
* add offline
* add offline
* fix
* fix
* fix default enable_thinking value
* fix default enable_thinking value
* modify condition
* Revert "modify condition"
This reverts commit 26430bdeb1
2025-08-19 10:50:01 +08:00
lizexu123
a053ab889b
[BugFix] fix num_running_requests in cuda_graph ( #3457 )
...
* fix cuda_grpah
* add note
---------
Co-authored-by: RAM <gstian5555@outlook.com >
2025-08-19 10:47:22 +08:00
AIbin
beec24fd89
【Inference Optimize】DeepSeek-v3 model inference performance optimization ( #3455 )
...
* DSK_OPT_01
* update FA3
2025-08-19 10:42:42 +08:00
zhuzixuan
c95b3395e9
【BugFix】completion接口echo回显支持 ( #3245 )
...
* wenxin-tools-511,修复v1/completion无法回显的问题。
* 支持多prompt的回显
* 支持多prompt情况下的流式回显
* 补充了 completion 接口支持 echo 的单元测试
* pre-commit
* 移除了多余的test文件
* 修复了completion接口echo支持的单测方法
* 补充了单元测试文件
* 补充单测
* unittest
* 补充单测
* 修复单测
* 删除不必要的assert.
* 重新提交
* 更新测试方法
* ut
* 验证是否是正确思路单测
* 验证是否是正确思路单测
* 验证是否是正确思路单测3
* 优化单测代码，有针对性地缩小单测范围。
* 优化单测代码2，有针对性地缩小单测范围。
* 优化单测代码3，有针对性地缩小单测范围。
* support 'echo' in chat/completion.
* update
* update
* update
* update
* update
* update
* 补充了关于tokenid的单元测试
* update
* 修正index错误
* 修正index错误
2025-08-19 10:41:51 +08:00
lizexu123
32b39620bc
[Code Simplification] remove cum_offsets ( #3410 )
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 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
2025-08-18 20:21:25 +08:00
luukunn
9c129813f9
[Feature] add custom chat template ( #3251 )
...
* add custom chat_template
* add custom chat_template
* add unittest
* fix
* add docs
* fix comment
* add offline chat
* fix unit test
* fix unit test
* fix
* fix pre commit
* fix unit test
* add unit test
* add unit test
* add unit test
* fix pre_commit
* fix enable_thinking
* fix pre commit
* fix pre commit
* fix unit test
* add requirements
2025-08-18 16:34:08 +08:00
Jundong Liu
70ee910cd5
[Excutor] Change cudagraph hashkey from batch size to num_tokens ( #3454 )
2025-08-18 16:16:48 +08:00
Jundong Liu
ea4a3b479c
[Excutor] Increase buffer size to prevent address corruption; add forward metadata debug tool ( #3404 )
...
* 修复buffer申请不够大，增加打印forwardmetadata的工具
* fix mistake
* Make CPU tensor in CPUPlace
* Add test about forward_meta_str and Add unitest_requirement
---------
Co-authored-by: RAM <gstian5555@outlook.com >
2025-08-18 16:14:09 +08:00
chen
5585cf7aa5
fix mtp_rej_topp input ( #3450 )
2025-08-18 16:12:42 +08:00
gaoziyuan
6fdd83da10
fix some bug ( #3434 )
2025-08-18 14:39:13 +08:00
freeliuzc
a12d0bc549
[Feature][MTP]update multi-draft-token strategy ( #3369 )
...
* update multi-draft-token strategy
* fix format
---------
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com >
2025-08-18 13:59:56 +08:00
chen
e88f5552db
fix cpu __ini__.py ( #3448 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-08-17 12:38:54 +08:00
chen
f0f00a6025
[OPs] Universal optimization and Fix early_stop cuda 700 ( #3375 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* delete nonzero
* delete setup_ops_base.py
* check if
* check gcp infer_seed.cpu()
* fix repetition_early_stopper_kernel cuda 700
2025-08-14 22:40:44 +08:00
YuanRisheng
09c979f3dd
[V1 Loader] Support Ernie text（moe and dense） ( #3110 )
...
* new loader support 0.3B
* fix weight
* support parallel load
* support parallel load
* fix slice
* support moe
* delete code
* perfect code
* perfect code
2025-08-14 20:25:28 +08:00
lzy
1e06b9fa6d
make append_attn supports mask_offset ( #3138 )
...
* make append_attn supports mask_offset
* add unittest
2025-08-14 03:40:55 -07:00
memoryCoderC
6031f9a5f5
[BugFix] fix ErnieProcessor not set raw_prediction ( #3400 )
2025-08-14 18:07:49 +08:00
lizexu123
7b596d0877
[BugFix] fix real_bsz in ep ( #3366 )
...
* Your commit message here
* fix ep
* delete cuda_graph
2025-08-14 17:31:19 +08:00
Jiang-Jia-Jun
666ab65a51
[Polish Code] Remove useless notes
2025-08-14 14:04:52 +08:00
Jiang-Jia-Jun
dd583fb16a
[BugFix] Fix default log level of paddleformers ( #3376 )
...
* [BugFix] Fix default log level of paddleformers
* [BugFix] Fix default log level of paddleformers
---------
Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com >
2025-08-14 11:36:24 +08:00
xiaolei373
d4f610e4cd
feat(log):add_request_and_response_log ( #3373 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-08-13 23:27:41 +08:00
ming1753
396dba0d62
[Bug Fix] Fix V1 video bug ( #3388 )
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-08-13 23:04:07 +08:00
Zero Rains
be94bdd0b0
[Loader V1] modify layername for DeepSeekV3 ( #3336 )
...
Co-authored-by: Yuanle Liu <yuanlehome@163.com >
Co-authored-by: YUNSHEN XIE <1084314248@qq.com >
2025-08-13 15:47:06 +08:00
EnflameGCU
d1a92e3e17
[GCU] Enable gcu CI ( #3190 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* [GCU] Update to the latest version
* [GCU] Enable CI
2025-08-13 11:48:24 +08:00
yzwu
ce9180241e
[Iluvatar GPU] Modify the names of some variables ( #3273 )
2025-08-13 11:38:02 +08:00
Kane2011
b4fef2cf29
[MetaxGPU] Support FastDeploy on metax gpu ( #3241 )
...
* [MetaxGPU] Support FastDeploy on metax gpu
* Update metax_worker.py
1. change worker log;
2. remove custom allreduce, adapt it later;
3. remove cuda graph;
* Update __init__.py
1. remove metax's key work comment
* Update __init__.py
1. remove metax's key word comment;
2. add fused_moe_kernel_paddle import
---------
Co-authored-by: yongqiangma <xing.wo@163.com >
2025-08-13 11:11:54 +08:00
luukunn
eda83ca672
add Tool Parser ( #3272 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* add tool-parser
* add tool-parser
* add tool parser
* add tool parser
* fix
* add offline
* add offline
* fix
* parsers:tool&reasoning
* 修改tool parser名称·
* update
* fix reasoning-parser
* add requirements
* fix finish reason
* fix
* fix reasoning-parser
* fix
* fix
* fix
* fix
* fix
---------
Co-authored-by: zhuzixuan <zhuzixuan@baidu.com >
2025-08-13 01:06:55 +08:00
memoryCoderC
2d1a4cacdf
Completion add raw_prediction/text_after_process ( #3356 )
2025-08-12 23:06:45 +08:00
memoryCoderC
c575611a5b
[BugFix] v1/completions add finish_reason ( #3246 )
...
* [BugFix] v1/completions add finish_reason
* update TestOpenAIServingCompletion for merge
---------
Co-authored-by: YUNSHEN XIE <1084314248@qq.com >
2025-08-12 19:40:26 +08:00
Jiang-Jia-Jun
90bfa0be9c
Update envs.py
2025-08-12 16:24:47 +08:00
Jiang-Jia-Jun
5620bd12de
Update envs.py
2025-08-12 16:24:33 +08:00
gaoziyuan
ccc7f1beb3
fix mapping ( #3320 )
2025-08-12 16:15:59 +08:00
RichardWooSJTU
283da92bfa
fix ep lm head ( #3244 )
...
Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com >
2025-08-12 15:38:28 +08:00
ming1753
f5164215be
[Bug Fix] fix vl V1 schedule bug ( #3323 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* [Bug Fix] fix vl V1 schedule bug
* fix format
2025-08-12 11:31:39 +08:00
chenjian
b21272d9ff
[Bug fix] fix block num setting in scheduler v1 for develop ( #3303 )
...
* fix block num setting in scheduler v1
* fix block num setting in scheduler v1
* fix max_block_num and max_num_batched_tokens setting
* fix max_block_num and max_num_batched_tokens setting
* fix max_block_num and max_num_batched_tokens setting
* fix max_block_num and max_num_batched_tokens setting
2025-08-12 10:38:51 +08:00
Jiang-Jia-Jun
183e3863e8
Remove useless code ( #3337 )
2025-08-12 10:32:31 +08:00
Zero Rains
b23af29d0b
Launch expert_service before kv_cache initialization in worker_process ( #3045 )
...
* launch expert_service before kv_cache initialization
* add two signal make sure model loading and expert_service lauching finished
* fix the EP bug
* fix ep
* update launching way
* fix ep
* update
* roback ep
* pre-commit all files
---------
Co-authored-by: RAM <gstian5555@outlook.com >
Co-authored-by: Divano <dddivano@outlook.com >
2025-08-11 19:38:46 +08:00
Jiang-Jia-Jun
c56c99837a
Revert "[BugFix] num_seqs ( #3291 )" ( #3316 )
...
This reverts commit e0aeac58e1
2025-08-11 16:16:51 +08:00
Yuanle Liu
9571c458f0
enhance eos_tokens ( #3274 )
...
* enhance eos_tokens
* update
* update
2025-08-11 14:47:52 +08:00
Zero Rains
42af0b4b64
[V1 Loader] Support DeepSeekV3(bf16) ( #3294 )
...
* Support new loader for DeepSeekV3(bf16)
* update paddle version
* remove useless attr
2025-08-11 13:39:28 +08:00
lizexu123
e0aeac58e1
[BugFix] num_seqs ( #3291 )
...
* fix num_seqs
* merge develop
2025-08-11 13:38:55 +08:00
chenjian
b88537a456
fix bug for scheduler v0 ( #3308 )
2025-08-11 13:07:04 +08:00
chen
46c8491201
merge logprob into batch_output ( #3266 )
2025-08-11 10:03:00 +08:00
chenjian
c011cb8b16
[Bug Fix] Fix scheduler bug in develop ( #3292 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* Fix scheduler bug in develop
* Fix scheduler bug in develop
* Fix scheduler bug in develop
2025-08-10 13:55:38 +08:00
ltd0924
31d4fcb425
[BugFix] fix too many open files problem ( #3256 )
...
Deploy GitHub Pages / deploy (push) Has been cancelled
* Update cache_messager.py
* fix too many open files problem
* fix too many open files problem
* fix too many open files problem
* fix ci bugs
* Update api_server.py
* add parameter
* format
* format
* format
* format
* Update parameters.md
* Update parameters.md
* Update serving_completion.py
* Update serving_chat.py
* Update envs.py
---------
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com >
2025-08-08 20:10:11 +08:00
