Commit Graph

2917 Commits

Author SHA1 Message Date
yinwei
d998efbc17 [Doc]Release fastdeploy-xpu 2.0.3 (#3408)
* fix v1 schedule oom bug

* fix v1 schedule oom bug

* update release note

* update info
v2.1.0
2025-08-14 19:19:54 +08:00
yinwei
8a15bdc0c8 [Doc]Release fastdeploy-xpu 2.1.0 (#3407)
* fix v1 schedule oom bug

* fix v1 schedule oom bug

* update release note
2025-08-14 19:11:16 +08:00
memoryCoderC
ad8ea68906 [BugFix] fix ErnieProcessor not set raw_prediction (#3401) 2025-08-14 19:10:07 +08:00
yinwei
101605869c [XPU] Fixed the issue of performance degradation caused by enabling ENABLE_V1_KVCACHE_SCHEDULER (#3393)
* fix v1 schedule oom bug

* fix v1 schedule oom bug
2025-08-14 17:41:40 +08:00
Jiang-Jia-Jun
28918702c2 Revert "Merge branch 'feature/online/vs_think_20250813' into release/2.1"
This reverts commit 02596fc537, reversing
changes made to 03347626a6.
2025-08-14 17:20:29 +08:00
Jiang-Jia-Jun
02596fc537 Merge branch 'feature/online/vs_think_20250813' into release/2.1 2025-08-14 17:13:36 +08:00
ltd0924
03347626a6 [BugFix] fix control signal release failed (#3374)
* [BugFix]

* [BugFix]

* [BugFix]

* [BugFix]

* fix

* fix

---------

Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-08-14 17:01:25 +08:00
YUNSHEN XIE
b2df0311b8 Optimize CI execution workflow. (#3371) (#3384)
* fix
2025-08-14 14:51:15 +08:00
xiaolei373
d1d321bafd feat(log):add_request_and_response_log (#3392) 2025-08-14 14:50:48 +08:00
Jiang-Jia-Jun
dc5d3ff5a0 [Polish Code] Remove useless notes 2025-08-14 14:05:29 +08:00
Jiang-Jia-Jun
f0a707e06f [BugFix] Fix default log level of paddleformers (#3377)
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-08-14 11:36:13 +08:00
JYChen
4870919682 fix stopseq error info (#3342)
Co-authored-by: YuBaoku <49938469+EmmonsCurse@users.noreply.github.com>
2025-08-14 10:45:05 +08:00
ming1753
a375378cc1 [Bug Fix] Fix V1 video bug (#3387) 2025-08-14 09:49:22 +08:00
YUNSHEN XIE
192f9caab4 Pre ce modified (#3335) (#3360)
* Pre ce modified (#3335)

* update

* update

* fix

* fix

* update

* update

* update

* fix

* update

* update

* update

* add ut fix pr(3367)
2025-08-13 18:50:52 +08:00
luukunn
81092c0fe3 add tool parser 2025-08-13 16:06:22 +08:00
YUNSHEN XIE
ad816f20f4 Use latest PaddlePaddle package (#3347) (#3352)
* Use latest PaddlePaddle package

* fix
2025-08-13 11:06:01 +08:00
memoryCoderC
37b76158f9 Completion add raw_prediction/text_after_process (#3362) 2025-08-12 23:20:36 +08:00
memoryCoderC
fe2094609f Release/2.1 (#3361)
* [BugFix] v1/completions add finish_reason

* update TestOpenAIServingCompletion for merge
2025-08-12 23:06:51 +08:00
gaoziyuan
b4bb54b56b bugfix (#3322) 2025-08-12 16:16:37 +08:00
Jiang-Jia-Jun
eeec4bd15e Remove useless code release/2.1 (#3338) 2025-08-12 11:32:50 +08:00
chenjian
d2592750f7 fix bug for scheduler v0 (#3306)
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
2025-08-12 00:41:15 +08:00
chenjian
25f51b0611 Fix block num in schduelr v1 for release 2.1 (#3315)
* fix bug for scheduler v0

* fix block num setting in scheduler v1 for release 2.1

* fix block num setting in scheduler v1 for release 2.1

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
2025-08-12 00:41:05 +08:00
ming1753
9b07f85f6d [Bug Fix] fix vl V1 schedule bug (#3284)
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: YUNSHEN XIE <1084314248@qq.com>
2025-08-12 00:40:45 +08:00
Sunny-bot1
2fe31c6f0f [Docs]fix sampling docs 2.1 (#3333)
* [Docs]fix sampling docs (#3113)

* fix sampling docs

* fix sampling docs

* update

* fix docs
2025-08-11 21:04:10 +08:00
YUNSHEN XIE
a33e557732 fix ci pypi index error (#3327) 2025-08-11 20:24:27 +08:00
kevin
054c790642 fix uvicorn multi worker error (#3309)
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-08-11 20:19:31 +08:00
Jiang-Jia-Jun
ca4e4ab911 Revert "[BugFix] fix ep (#3290)" (#3317)
This reverts commit 86ff68be4b.
2025-08-11 16:17:58 +08:00
chenjian
c000cff744 fix scheduler bug in release2.1 (#3295) 2025-08-10 13:55:22 +08:00
lizexu123
86ff68be4b [BugFix] fix ep (#3290)
* fix ep

* fix
2025-08-09 16:32:35 +08:00
yinwei
702c313ed1 revert pr (#3286) 2025-08-09 16:29:35 +08:00
ltd0924
6706ccb37e [BugFix] fix too many open files problem (#3275) 2025-08-08 20:11:32 +08:00
JYChen
1b6f482c15 [Cherry-pick] fix stop seq (#3263)
* fix out-bound value for stop sequence

* catch error if there are out-of-bounds value

* check in offline mode
2025-08-07 19:11:37 +08:00
sg263
5d3bf308f6 merge develop trace FD_START (#3253)
Co-authored-by: shige <shige@baidu.com>
2025-08-07 11:10:55 +08:00
Sunny-bot1
f672a34f95 [FIX 2.1]fix bad_words when sending requests consecutively (#3199)
* fix bad_words

* fix log

* fix log
2025-08-06 15:47:27 +08:00
lizexu123
bc0b92bba4 [BugFix] support real batch_size (#3109) (#3217)
* support real bsz

* fix

* fix xpu_model_runner.py,gpu_model_runner.py,gcu_model_runner.py,iluvatar_model_runner.py

* add event_loop_ep

* fix

* Add comments

* fix

* support mtp real_batch_size

* fix

* self.tmp_seq_lens_this_time->self.seq_lens_this_time_buffer

* fix

* fix VL real_seq_lens_this_time

* fix

* fix mtp

* fix

* fix mtp

* fix xpu

* fix
2025-08-06 14:30:33 +08:00
SunLei
3dd8492601 [Bugfix] Fix uninitialized decoded_token and add corresponding unit test (#3201)
* Update test_base_chat.py (#3183)

* [Bugfix] Fix uninitialized decoded_token and add corresponding unit test.

---------

Co-authored-by: Divano <dddivano@outlook.com>
2025-08-05 10:55:22 +08:00
RAM
bd77a3a643 [Bug Fix] Fix bug of MLA Attention Backend (#3178)
* fix typo

* fix mla attention backend
2025-08-05 10:53:27 +08:00
YUNSHEN XIE
9561603ed9 Apply CI fix from Develop (#3151)
* fix ci approve

* Describe PR diff coverage using JSON file (#3114)

* Refactored ci pipeline

* update

* Describe PR diff coverage using JSON file

* remove pip cache setting from Approve

* fix

* update

* fix ci (#3141)

* fix
2025-08-04 16:30:56 +08:00
plusNew001
e26313a355 Update Dockerfile.xpu (#3147) 2025-08-04 16:25:33 +08:00
yinwei
4367c09a5f Fix out-of-memory issue during single-XPU deployment (#3131) 2025-08-04 16:02:43 +08:00
bukejiyu
8e789dcb67 fix load_pre_sharded_checkpoint (#3152) (#3169)
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-08-04 15:44:10 +08:00
ltd0924
5f6fc7f7b9 Update cache_messager.py (#3173) 2025-08-04 15:09:17 +08:00
RAM
d4059cabf0 fix typo (#3153) 2025-08-01 22:34:59 +08:00
chen
c8dd5976ae fix request_output sampling_params (#3154) 2025-08-01 22:34:33 +08:00
Jiang-Jia-Jun
4880c16be3 Update setup.py 2025-07-31 20:30:24 +08:00
SunLei
dade19d7a4 [Feature] General support for logprobs (#2974)
* [Feature] support logprobs in chat/completions and completions endpoints

* Temporarily comment out text_offset due to incorrect logic

* Clean up temporary debug prints

* [Feature] support logprobs in offline mode via SamplingParams

* fix: serialize Logprob as dict before zmq send to fix msgpack error

* refactor: remove redundant methods to simplify codebase

* Fix missing fields in CompletionOutput.to_dict affecting msgpack serialization

* refactor: centralize param validation in engine_client to reduce duplication

* revert: rollback changes in offline_demo.py

* revert: rollback changes in offline_demo.py

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

* [bugfix] fix parameter validation for logprobs

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-07-31 20:25:56 +08:00
chenjian
fe17410f9c [BUG] Fix bug for pd in fd (#3034)
* Fix bug for pd in fd

* Fix bug for pd in fd

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-07-31 20:17:27 +08:00
Zhang Yulong
1a543bca29 Fix test_EB_Lite_serving.py (#3119)
* Fix test_EB_Lite_serving.py

* fix test_EB_Lite_serving.py
2025-07-31 20:15:25 +08:00
Yuan Xiaolan
5f56d289a7 fix is_permuted (#3098)
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-07-31 19:58:05 +08:00
LiqinruiG
25005fee30 [Doc] add chat_template_kwagrs and update params docs (#3103)
* add chat_template_kwagrs and update params docs

* add chat_template_kwagrs and update params docs

* update enable_thinking

* pre-commit

* update test case

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-07-31 19:44:06 +08:00