apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
2,900 Commits 29 Branches 10 Tags
fe2094609ff886e20f2a3d4f282db23d96dfd738
Commit Graph

2900 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
kevin
22cab724e8 [Feature] block scheduler v1 support prefix caching (#3061) 
* block scheduler v1 support prefix cache

* update code

* update code

* fix code bug

* add timeout time

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
 2025-07-31 19:29:19 +08:00
chenjian
32307283f1 Fix bug for offline inference in scheduler v1 (#3117) 2025-07-31 17:54:24 +08:00
YUNSHEN XIE
583eae2fd1 fix ci (#3106) 
* fix ci

* disable test_non_streaming_chat_with_min_tokens
 2025-07-31 17:25:08 +08:00
JYChen
1ef38b1563 [doc] best practice for eb45 text models (#3002) 
* [doc] best practice for eb45 text models

* fix docs
 2025-07-31 17:21:55 +08:00
Jiang-Jia-Jun
4498058722 Update README.md 2025-07-31 15:33:12 +08:00
Jiang-Jia-Jun
66304cf921 Update sampling.md 2025-07-31 15:02:57 +08:00
yinwei
5b9aec1f10 xpu release 2.0.3 (#3105) 2025-07-31 14:26:07 +08:00
YUNSHEN XIE
66c3835a46 add approve ci (#3093) 
* add approve ci

* fix

* fix
 2025-07-31 10:10:10 +08:00
RAM
d850660872 [Executor] Refactor GetBlockShapeAndSplitKVBlock Kernel (#2989) 
* reset decoder_block_shape_q buffer

* refactor GetBlockShapeAndSplitKVBlock Kernel and cudagraph padding batch

* update decode_max_tile_size

* fix pre-commit

* update block_multihead_attn_backend

* update flas attn backend

* update MLA Attention

* update XPU Attention

* update gcu,iluvatar model runner

* Update MTP

* fix MTP bug
 2025-07-31 00:09:31 +08:00
Jiang-Jia-Jun
998968f1e8 [Doc] Update parameters of serving 2025-07-30 22:35:01 +08:00
chenjian
fe0e3f508b [BUG FIX] Fix bug when preempted request rescheduled (#3080) 
* Fix bug when preempted request rescheduled

* Fix bug when preempted request rescheduled

* Fix bug when preempted request rescheduled
 2025-07-30 22:25:47 +08:00
Jiang-Jia-Jun
0616c208d2 [Feature] Support include_stop_str_in_output in completion api (#3096) 
* [Feature] Support include_stop_str_in_output in completion api

* Fix ci test

---------

Co-authored-by: Jiang-Jia-Jun <jiangjiajun@baidu.com>
 2025-07-30 22:18:48 +08:00
YuanRisheng
7dfdd157ac [BugFix]Fix ep size (#3092) 
* fix ep

* fix num_layer
 2025-07-30 21:03:12 +08:00
ltd0924
d17886de19 [Feature] support ep in mixed mode (#3001) 
* [LLM] support ep

* Update worker_process.py

* Update expert_service.py

* Update worker_process.py

* format files
 2025-07-30 20:43:39 +08:00
JYChen
bd29b2aaca add stop_seqs doc (#3090) 2025-07-30 20:36:18 +08:00
Jiang-Jia-Jun
6ead7a3a49 Update setup.py 2025-07-30 20:21:41 +08:00
YUNSHEN XIE
e4ba9a0dde debug use (#3095) 2025-07-30 20:18:36 +08:00