Commit Graph

163 Commits

Author SHA1 Message Date
chen
cc588b70ab [CP][BugFix]Dev fix custom ar unstable result (#5186)
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
* [CP][BugFix]Dev fix custom ar unstable result (#4437)

* code check

* revert delete

* check

* pre_commit
2025-11-24 15:28:01 +08:00
kevin
966297e5d6 [Feature] mm prefix cache (#4554)
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
* mm prefix cache

* add _revert_match_blocks

* update code

* update code

* update code

* fix bugs

* add test case

* fix bug

* update code

* update reserved_dec_block_ids
2025-11-19 19:32:14 +08:00
LiqinruiG
24a7b79eec [BugFix] rollback max_tokens and min_tokens when continue to infer (#5051)
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
Co-authored-by: liqinrui <liqinrui@baidu.com>
2025-11-15 16:40:35 +08:00
kxz2002
936a80962f [BugFix] adjust max_tokens and min_tokens when continue to generate tokens (#5010) (#5015)
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
* fix max and min tokens initial commit

* fix double subtraction

* add unit tests

Co-authored-by: gaoziyuan <88373061+gzy19990617@users.noreply.github.com>
2025-11-14 22:24:59 +08:00
kxz2002
e0d98d00bc [Cherry-Pick] Modify follow-up push parameters and Modify the verification method for thinking length (#4086) (#4826)
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
* resolve #4086 conflict

* fix unit test
2025-11-05 21:36:28 +08:00
xiaoxiaohehe001
ee37882a26 [NewFeature] support eplb noaux (#4725)
* support eplb noaux

* support eplb noaux

* add  eplb noaux test
2025-11-05 20:59:12 +08:00
RAM
7847b44172 [Graph Optimization] Refactor default capture list (#4631)
* refactore default capture list & refine code

* fix bug

* fix ci bug

* Fix test case
2025-10-31 14:18:27 +08:00
freeliuzc
c9be8762b6 [MTP]Merge support attn (#4591)
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
* support mask_offset in speculate decoding

* fix dummpy run output

* add unit test

* fix unit test import
2025-10-27 21:13:08 +08:00
GoldPancake
2cf0b0b715 [Feature] support mtp distribution equivalence verification (#4566)
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
* support mtp distribution equivalence verification

* fix bugs

* add unit test
2025-10-27 11:01:28 +08:00
kevin
fdce0d2299 add test case
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
2025-10-23 15:20:21 +08:00
guozhuangzhuang
1531004085 fix image token output (#4487)
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
* fix

* fix

* fix

* add test case

* add test case

* add test case
2025-10-22 14:59:05 +08:00
YuBaoku
31ac6c62f8 [CI] update ernie-4_5-vl baseline (#4495) (#4505)
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
* [CI] update ernie-4_5-vl baseline
2025-10-21 20:06:39 +08:00
freeliuzc
c3499875bd [MTP]support mtp chunk_prefill_v1 (#4365)
* support mtp chunk_prefill_v1

* fix mtp chunkprefill output

* fix mtp chunkprefill output, fix unit test

* fix save_output

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-10-15 15:33:59 +08:00
YuBaoku
0bfffdbc14 [CI] remove test_common_model (#4196) 2025-09-23 14:23:05 +08:00
Yuan Xiaolan
25aa2d94aa cp dynamic Cfp8 (#4120)
* supports dynamic Cfp8

* add unittest

* fix dynamic Cfp8 computing error

* fix Cfp8 for RL load

---------

Co-authored-by: carryyu <569782149@qq.com>
2025-09-17 11:55:47 +08:00
gaoziyuan
10768a4d79 [NewFeture]add ep rollout model init and update/clear ep buffer (#3927)
* add ep rollout model init && add deep update/clear

* fix test
2025-09-12 14:15:13 +08:00
guozhuangzhuang
f06e3ee1fc Use uuid to name the metrics shared folder (#4025)
* Use uuid to name the metrics shared folder

* Use uuid to name the metrics shared folder test case
2025-09-10 16:58:13 +08:00
freeliuzc
2f473ba966 [Feature][MTP]Support MTP for rl-model (#4009)
* qk norm for speculate decode C16

* support mtp in v1_scheduler mode

* support mtp rope_3d

* support mtp features

* add unit test && del some log

---------

Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com>
Co-authored-by: xiaoxiaohehe001 <hiteezsf@163.com>
2025-09-10 13:34:37 +08:00
Zhang Yulong
8903f937f9 update ci (#3953) 2025-09-08 14:21:25 +08:00
bukejiyu
051e4a881c ignore (#3949) 2025-09-07 23:57:48 +08:00
chenjian
41cd3e24c9 [Feature] Enable prefix caching as default (#3816)
* [Feature] Enable prefix caching as default

* [Feature] Enable prefix caching as default

* Set prefix caching as default

* skip dynamic load

* fix kill bug

* fix kill bug

* fix kill bug

* fix ci

* fix

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-09-06 09:51:34 +08:00
Zhang Yulong
11b18e5ef0 add cache queue port (#3904) (#3926)
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
* add cache queue port

* add cache queue port

* add cache queue port
2025-09-06 00:00:12 +08:00
chenjian
fb1e0d6a87 [Feature] Set scheduler v1 as default (#3812)
* [Feature] Set scheduler v1 as default

* [Feature] Set scheduler v1 as default

* [Feature] Set scheduler v1 as default

* [Feature] Set scheduler v1 as default

* [Feature] Set scheduler v1 as default

* [Feature] Set scheduler v1 as default
2025-09-04 11:02:10 +08:00
SunLei
8c0e7d6fe9 Support for async processor added. (#3870)
* Support for async processor added.

* remove yappi code
2025-09-04 10:35:08 +08:00
yangjianfengo1
b56b015d85 fix port (#3865)
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-09-04 10:02:08 +08:00
lizhenyun01
bed09ae8f8 fix mask_offset in append_attn (#3745)
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 mask_offset in append_attn

* fix test
2025-08-31 15:03:16 +08:00
SunLei
b9af95cf1c [Feature] Add AsyncTokenizerClient&ChatResponseProcessor with remote encode&decode support. (#3674)
* [Feature] add AsyncTokenizerClient

* add decode_image

* Add response_processors with remote decode support.

* [Feature] add tokenizer_base_url startup argument

* Revert comment removal and restore original content.

* [Feature] Non-streaming requests now support remote image decoding.

* Fix parameter type issue in decode_image call.

* Keep completion_token_ids when return_token_ids = False.

* add copyright
2025-08-30 17:06:26 +08:00
lizexu123
b21e085f3e [Code Simplification] delete print (#3729) 2025-08-30 16:19:07 +08:00
lizexu123
455205f991 [Features] support hugging face qwen3 moe (#3649)
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
* split ut

* qwen3-30B-A3B

* fix

* add test

* add test_torch_model.py

* fix test_torch_model.py

* delete print

* fix moe

* delete init.py

* fix

* fix

---------

Co-authored-by: bukejiyu <395822456@qq.com>
Co-authored-by: bukejiyu <52310069+bukejiyu@users.noreply.github.com>
2025-08-30 15:26:05 +08:00
YUNSHEN XIE
a18afcfdd9 Optimize coverage jobs (#3683)
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
2025-08-30 00:12:40 +08:00
yangjianfengo1
3754a9906d [Feature] block sparse attention (#3668)
* 支持稀疏attn

* fix bug

* code style

* fix moba attn get kv shape

* 修复a100编译

* codestyle

* code style

* code style

* code style

* fix conflict

* 增加单侧

* code style

* 增加eblite 加载时间

* fix bug

* for ci

* for ci

* for ci

* for ci

* 支持mlp block size 128

* 增加小算子单测

* fix 单测 mlp

* 将环境变量加入到config里面

* fix rollout config

* 修复显存

* add test server

* add test server

* fix mlp  最后一层使用full attn
2025-08-29 19:46:30 +08:00
Yuan Xiaolan
c71ee0831c add w4afp8 offline script (#3636) 2025-08-29 17:56:05 +08:00
Ryan
45f81b34f0 add dtype int32 (#3692)
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
2025-08-29 14:56:35 +08:00
李泳桦
88297240e7 [feat] completion api supports passing input token ids in either prompt or prompt_token_ids (#3311)
* [feat] completion api supports passing input token ids in either `prompt` or `prompt_token_ids`

* [fix] update comment

* [fix] fix type error

* [test] add a unittest file for serving api test

* [test] try to fix ci error

* [chore] rename test function names

* [test] try to fix ci error

* [test] try to fix ci error

* [test] add tests for qwen
2025-08-29 14:19:42 +08:00
周周周
17b414c2df MoE Default use triton's blockwise fp8 in TP Case (#3678) 2025-08-29 11:07:30 +08:00
Echo-Nie
43d5bd62b4 【Hackathon 9th No.70】supplementary unit test for CPUPlatform and CUDAPlatform (#3580)
* 功能模块 CUDAPlatform、CPUPlatform 单测补充

* update the "is_cuda" to "is_cuda_and_available"

* fix pre-commit

---------

Co-authored-by: Tao Luo <luotao02@baidu.com>
2025-08-29 10:34:05 +08:00
Yuanle Liu
4957908275 add input_processor plugin (#3657)
* add input_processor plugin

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update
2025-08-28 22:53:57 +08:00
Divano
17731a8acd add concurrency cases (#3689) 2025-08-28 18:30:19 +08:00
Liumengyuan
e93d4cfcdd Add with_output version AppendAttention (#3302)
* get use_output from fd_config

* add clear TODO description

* add mask_offset para to align with develop

* fix bug

* fix use_output logic

* fix sot bug
2025-08-28 17:10:18 +08:00
bukejiyu
73cf6096da fix (#3676)
* fix

* update
2025-08-28 17:06:32 +08:00
co63oc
d4fc893fe3 fix typos (#3633)
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-08-28 14:42:24 +08:00
Echo-Nie
7afcd4b776 【Hackathon 9th No.77】supplementary unit test for get_filtered_metrics (#3578)
* 功能模块 fastdeploy/metrics/metrics/get_filtered_metrics 单测补充

* fix pre-commit

---------

Co-authored-by: Tao Luo <luotao02@baidu.com>
2025-08-28 10:39:02 +08:00
ltd0924
3d92fb09f7 [BugFix] fix parameter is 0 (#3592)
* Update engine_client.py

* fix

* Update common_engine.py
2025-08-28 09:52:36 +08:00
Sunny-bot1
479c8b85d3 [Optimize]support machete weight only gemm (#3561)
* support machete weight only gemm

* add generate

* update

* fix

* change file location

* add sm_version limit

* fix

* fix

* fix ci

* fix coverage

* fix xpu
2025-08-28 09:49:58 +08:00
Zero Rains
e37e86b3b8 [V1 Loader]support param create and load for wint2 and xpu backend (#3581)
* support wint2 backend'

* [V1 Loader]support param create and load for wint2 and xpu backend

* update weight shape name

* update

* update

* update baseline.txt

* update model name

* update baseline.txt

* fix codestyle

* remove debug coode
2025-08-28 09:49:36 +08:00
Jiang-Jia-Jun
c694fa2879 Revert "[Feature] block sparse attention (#3209)" (#3647)
This reverts commit 646a0c2fd8.
2025-08-27 17:35:04 +08:00
lzy
1265f6c192 deepgemm don't support tp+ep (for ci) (#3638)
* deepgemm don't support tp+ep (for ci)

* deepgemm don't support tp+ep (for ci)
2025-08-27 16:39:19 +08:00
xjkmfa
afb9f327ef 【CI case】for echo finish_reason text_after_process and raw_prediction check (#3630)
* Add ci case for min token and max token

* 【CI case】include total_tokens in the last packet of completion interface stream output

* echo&finish_reason&text_after_process&raw_prediction check

* echo&finish_reason&text_after_process&raw_prediction check

* echo&finish_reason&text_after_process&raw_prediction check

* echo&finish_reason&text_after_process&raw_prediction check

* echo&finish_reason&text_after_process&raw_prediction check

---------

Co-authored-by: xujing43 <xujing43@baidu.com>
2025-08-27 15:21:16 +08:00
YUNSHEN XIE
85afa72763 fix publish task (#3635)
* fix publish task

* disable ut
2025-08-27 11:14:53 +08:00
yangjianfengo1
646a0c2fd8 [Feature] block sparse attention (#3209)
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
* 支持稀疏attn

* fix bug

* code style

* fix moba attn get kv shape

* 修复a100编译

* codestyle

* code style

* code style

* code style

* fix conflict

* 增加单侧

* code style

* 增加eblite 加载时间

* fix bug

* for ci

* for ci

* for ci

* for ci

* 支持mlp block size 128

* 增加小算子单测

* fix 单测 mlp

* 将环境变量加入到config里面

* fix rollout config
2025-08-26 07:16:04 -07:00