Commit Graph

60 Commits

Author SHA1 Message Date
RAM
fbed0ef851 [Cherry-Pick][RL] Support Rollout Routing Replay (#5166)
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 r3

* update

* support tp>1&&ep>1

* support cudagraph padding

* support all backends

* replace env with options

* modularize

* update

* Add RoutingStore and refine code

* add routing replay cofig

* add routing repaly config

* success run routing store

* convert request id as rollout id

* fix rollout config bug

* unify code

* use rollout_id to replace request_id in routing store

* delete code

---------

Co-authored-by: yuanlehome <yuanlehome@163.com>
2025-12-04 00:35:30 -08:00
kevin
74ba637b6b remove close prefix cache (#5363)
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
2025-12-03 20:59:32 +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
kevin
3ce2c8f754 [Feature] support async download features (#4910)
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 async download

* update code

* fix bug

* update code

* update code

* fix bugs

* update code

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-11-18 18:37:59 +08:00
kevin
3dbe5596e6 [Feature] Support eplb for ep (#4786)
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 eplb for ep

* update code

* update code

* update code

* update code

* update code

* update code

* update code

* update code

* update code
2025-11-07 15:42:29 +08:00
Yuan Xiaolan
1e88754133 support set dy-C8 from args (#4475)
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
2025-11-04 17:01:35 +08:00
lizhenyun01
006c7e5a0d [Feature] Support attention dp balance for mixed deployment (#4594)
* [Feature] Support attention dp balance for mixed deployment

* add abstractmethod

* add config to rl

* fix argument style
2025-10-29 15:23:51 +08:00
GoldPancake
9c7187998c [Feature] support mtp logprob (#4457)
* support logprob in mtp

* remove debug code

* fix

* feat: add draft_logprobs for Speculative Decode MTP

* Revert "feat: add draft_logprobs for Speculative Decode MTP"

This reverts commit d5a3c5c933.

* fix

* feat: add draft_logprobs for Speculative Decode MTP

* feat: add draft_logprobs for Speculative Decode MTP

* fix some bugs

* fix codestyle

* fix bugs

* fix bugs

* fix bugs

* fix bus

* fix bugs

* fix unitest

---------

Co-authored-by: sunlei1024 <sunlei5788@gmail.com>
Co-authored-by: sunlei18 <sunlei18@sunlei18deMacBook-Pro.local>
2025-10-20 10:18:00 +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
ltd0924
28aa18bfc1 [Feature] support prefix cache + dp (#4356)
* fix

* fix

* fix

* [Feature] support clear data

* update

* fix

* fix

* fix

* fix

* [BugFix] fix clear data

* Update api_server.py

* Update api_server.py

* [Feature] support fd decode response

* Update engine.py

* Update envs.py

* Update expert_service.py

* Update common_engine.py

* [Feature] support prefix cache + ep

* fix

* add

* Update expert_service.py

* Update common_engine.py

* Update common_engine.py

* Update common_engine.py

* Update common_engine.py

* Update common_engine.py

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
Co-authored-by: ltd0924 <luotingdan@baidu.com>
2025-10-11 10:02:08 +08:00
freeliuzc
e2b68b33c9 fix mtp in rl (#4234)
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
2025-09-24 16:59:24 +08:00
lzy
be98f6e950 supports internode_ll_two_stage (#4143)
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
* supports internode_ll_two_stage

* supports internode_ll_two_stage

* supports internode_ll_two_stage

* supports internode_ll_two_stage
2025-09-22 14:55:06 +08:00
chen
2485333f71 ep support logprob (#4089)
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
2025-09-12 21:11:16 +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
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
Yuanle Liu
71a9127e13 Update args_utils.py 2025-09-08 01:41:43 -07:00
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
yinwei
77c1bd0813 [XPU]Fixed the issue of performance degradation caused by enabling ENABLE_V1_KVCACHE_SCHEDULER (#3900)
* fix bug

* fix bug

* update

* udpate

* update
2025-09-05 19:17:25 +08:00
chenjian
8567ada09e [Fix] disable scheduler v1 in guided decoding (#3877)
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
* disable scheduler v1 in guided decoding

* disable scheduler v1 in guided decoding
2025-09-04 20:54:55 +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
kevin
a86b35ab49 Fix chunked prefill (#3778)
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
* update enable chunked_prefill

* update code

* update code

* update code
2025-09-02 13:41:55 +08:00
kevin
753772ace8 default enable chunked prefill (#3731)
* add error traceback info

* update error msg

* update code

* default enable chunked prefill

* update code

* update code

* add envs

* update code

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-08-31 13:15:13 +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
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
Jiang-Jia-Jun
c694fa2879 Revert "[Feature] block sparse attention (#3209)" (#3647)
This reverts commit 646a0c2fd8.
2025-08-27 17:35:04 +08:00
chen
ce9c0917c5 [Precision] Support lm_head layer running in float32 (#3597)
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 lm_head fp32 bf16 fp16

* support lm_head fp32 bf16 fp16

* add doc and check code

* lm_head_fp32 specify lm_head as fp32

* code check

* check doc
2025-08-27 11:34:53 +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
gaoziyuan
82e64b13e1 [NewFeature]Support dp multi api server && Fix some bug in mixed ep && merge develop (#3598)
* [Feature] update ep

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix queue ports idx

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* fix ci

* Update engine.py

* fix ci

* fix some bug in mixed ep

* add server fix and op fix

* rm some log

* fix code style

* ltd fix

* fix

* fix

* fix some bug

* fix bug

* fix bug

* fix style

* Update config.py

* Update splitwise_connector.py

* Update cache_messager.py

* Update __init__.py

* merge and fix

* Update engine.py

* Update common_engine.py

* Update run_ci_xpu.sh

* Update ernie_processor.py

* Update ernie_processor.py

---------

Co-authored-by: ltd0924 <ltd0924@sina.com>
Co-authored-by: ltd0924 <32387785+ltd0924@users.noreply.github.com>
2025-08-26 19:59:02 +08:00
lizexu123
c43a4bec00 [Features] support hugging face qwen3 dense and qwen2 model (#3574)
* support qwen2 and qwen3 hugging face

* fix moe

* defualt_v1 loader

* hugging_face_format deprecated

* modify hugging_face_foramt to model_format

* model_format auto

* fix environemt

* fix bug

* fix qwen3-0.6 bug

* model_format is str

* fix
2025-08-26 10:54:53 +08:00
zhink
df7c31012b Modified to support custom all reduce by default (#3538) 2025-08-22 16:59:05 +08:00
YuanRisheng
c389a4013c Unify server-side and model-side Config(Part-5) (#3497)
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 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
* move config

* fix xpu

* fix

* fix vl

* fix vl

* fix unitest

* fix args

* add unitest

* fix test
2025-08-21 19:00:21 +08:00
Yzc216
466cbb5a99 [Feature] Models api (#3073)
* add v1/models interface related

* add model parameters

* default model verification

* unit test

* check model err_msg

* unit test

* type annotation

* model parameter in response

* modify document description

* modify document description

* unit test

* verification

* verification update

* model_name

* pre-commit

* update test case

* update test case

* Update tests/entrypoints/openai/test_serving_models.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update tests/entrypoints/openai/test_serving_models.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update tests/entrypoints/openai/test_serving_models.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update tests/entrypoints/openai/test_serving_models.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update fastdeploy/entrypoints/openai/serving_models.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: LiqinruiG <37392159+LiqinruiG@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-08-21 17:02:56 +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
luukunn
eda83ca672 add Tool Parser (#3272)
Some checks failed
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
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
chen
46c8491201 merge logprob into batch_output (#3266) 2025-08-11 10:03:00 +08:00
lizexu123
afff4d37ea [Feature] support seed parameter (#3161)
* support seed

* fix

* add SamplingMetadata seed test

* The next_tokens values are inconsistent!

* add air and rejection seed test

* fix

* add SamplingParams seed test

* fix seed=0

* Default to defualt

* fix

* fix args_utils

* fix review

* fix review

* fix

* fix

* add xpu,gcu,iluvatar support seed

* fix
2025-08-06 15:20:47 +08:00
ApplEOFDiscord
b71cbb466d [Feature] remove dependency on enable_mm and refine multimodal's code (#3014)
* remove dependency on enable_mm

* fix codestyle check error

* fix codestyle check error

* update docs

* resolve conflicts on model config

* fix unit test error

* fix code style check error

---------

Co-authored-by: shige <1021937542@qq.com>
Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-08-01 20:01:18 +08:00
bukejiyu
db698bda01 qwen loader (#3057) 2025-07-30 19:09:38 +08:00
YuanRisheng
99a70fc722 unify parallel config (#3070) 2025-07-30 11:41:23 +08:00
Zero Rains
b2f9a42d87 [Feature] Support repetition early stop (#3024)
* support repetition early stop and support user to set the parameter

* remove log

* fix codestyle

* add the early_stop_config to rollout_config

* update config and EarlyStopper class

* fix the bug for triton

* modify the stop method

* update description

* modify the usage for stop_flags

---------

Co-authored-by: Yuanle Liu <yuanlehome@163.com>
2025-07-29 22:42:54 +08:00
YuanRisheng
502ee92a0a Unify server-side and model-side Config (Part3) (#3047)
* merge model config

* fix arch

* fix rl
2025-07-29 17:07:44 +08:00
YuanRisheng
bddf403576 Unify server-side and model-side Config (Part2) (#3035)
* merge speculative and graph opt conifg

* add attr
2025-07-28 15:31:48 +08:00
YuanRisheng
6ccc10ad47 Unify server-side and model-side Config (Part1) (#3018)
* move cache config

* fix mtp
2025-07-28 10:51:52 +08:00
Zero Rains
0fb37ab7e4 update flake8 version to support pre-commit in python3.12 (#3000)
* update flake8 version to support pre-commit in python3.12

* polish code
2025-07-24 01:43:31 -07:00
ltd0924
f935d6f862 [BugFix] fix multinode deployment (#2977) 2025-07-24 15:04:04 +08:00
Yzc216
e14587a954 [Feature] multi-source download (#2986)
* multi-source download

* multi-source download

* huggingface download revision

* requirement

* style

* add revision arg

* test

* pre-commit
2025-07-24 14:26:37 +08:00
chenjian
85a78d695d [Feature] Support block scheduler v1 for FD (#2928)
* Support FD block scheduler v1

* Support FD block scheduler v1

* Support FD block scheduler v1

* Fix according to copilot review

* Fix according to review

* Remove is_dummy

* Fix bug when real_bsz=1

* Fix infer first token cost time

---------

Co-authored-by: Jiang-Jia-Jun <163579578+Jiang-Jia-Jun@users.noreply.github.com>
2025-07-23 20:31:31 +08:00
Zero Rains
89a485b69f [Feature] Support using prefix-caching + cudagraph for inference (#2924)
* fix the bug in cudagraph+prefix-caching but still have some bug with profile

Change-Id: Ibf2ba3f2e3b08641d03f4b1391d7c862c3efa397

* add the signal to make sure cache manager launched

* fix judge condition

* reomove useless control

* update control stream

* update

* fix xpu

* change the do_profile flag

* update

* add new threads to init cache_manager

---------

Co-authored-by: RAM <gstian5555@outlook.com>
2025-07-22 00:59:45 -07:00
zhink
0262ef7eb3 custom all reduce support cuda graph (#2938)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
* Support enabling cuda graph and custom all reduce at the same time, and fix the overwritten custom all reduce flag

* rename communication_op to communication
2025-07-21 22:52:03 +08:00