louis_lifu
/
AReaL
mirror of https://github.com/inclusionAI/AReaL
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
257 Commits 12 Branches 4 Tags 21 MiB
Commit Graph

257 Commits

Author SHA1 Message Date
博惟 2755fc9d8c . 2025-03-28 17:07:15 +08:00
博惟 c9c2c79370 . 2025-03-28 17:03:25 +08:00
bowei.fw 111211b302 . 2025-03-28 16:44:56 +08:00
bowei.fw 1649c9fcf1 . 2025-03-28 16:36:03 +08:00
bowei.fw a568dd0e5a . 2025-03-28 16:34:03 +08:00
郭唯 cc83c84e29 PullRequest: 65 Fix config reader for cli 
Merge branch fix-cli of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/65

Signed-off-by: 博惟 <bowei.fw@antgroup.com>
 2025-03-28 15:18:25 +08:00
kira.gw f686048f5f fix config reader for cli 2025-03-28 15:00:13 +08:00
博惟 0bd9969ec4 PullRequest: 62 [Patch v0.2.0] Move all CLI arguments into a single file and add pretty helper messages. 
Merge branch fw/cli-args of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/62

Signed-off-by: 郭唯 <kira.gw@antgroup.com>


* .
* format and test
* .
* .
* .
* .
* run
* .
* .
* add runtime helper message
* .
* .
 2025-03-28 12:00:37 +08:00
郭唯 71429c9655 PullRequest: 63 simplify startup command 
Merge branch simplify-startup of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/63?tab=diff

Signed-off-by: 博惟 <bowei.fw@antgroup.com>
 2025-03-28 11:25:26 +08:00
bowei.fw 68d8e860a3 format 2025-03-28 11:24:37 +08:00
kira.gw 86d08db879 fix var name 2025-03-28 11:20:21 +08:00
kira.gw c2b03f62d6 rename preset to prologue 2025-03-28 11:18:00 +08:00
kira.gw 62b9bf3f44 simplify startup command 2025-03-28 11:09:44 +08:00
博惟 9b9b0af9c3 PullRequest: 61 [Patch v0.2.0] Fix the PPO bug in old environments. 
Merge branch fw/patch20250326 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/61

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
* .
* .
 2025-03-28 09:58:26 +08:00
君末 f8afa97484 PullRequest: 49 Enable Parallel Execution for Code, Math, and Reference Tasks 
Merge branch async-ref-rew of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/49

Signed-off-by: 博惟 <bowei.fw@antgroup.com>
 2025-03-28 09:40:54 +08:00
meijun 5773645acd fix review issue 2025-03-27 21:43:17 +08:00
meijun.mei abfe8bd30f update dataset for fused-refrw 2025-03-27 18:38:22 +08:00
meijun.mei fc79f21622 update examples script for fuse-ref-rw 2025-03-25 18:18:57 +08:00
博惟 9f77f96580 PullRequest: 58 Support ETCD3 name resolving repo 
Merge branch fw/etcd of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/58

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
* .
* .
* .
* .
* .
* .
 2025-03-25 16:05:04 +08:00
博惟 6ccbb01ca8 PullRequest: 56 Support the cuda 12.8 image with megatron v0.11.0 and SGLang 0.4.4 
Merge branch fw/megatron-v0.11.0 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/56

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* update trial
* add moe test script
* .
* .
* .
* .
* .
* .
* .
* .
* .
* remove gae2d
* .
 2025-03-25 16:02:10 +08:00
博惟 46b7d3d32b PullRequest: 59 Disable sliding window and chunked prefill for vLLM by default 
Merge branch fw/fix-vllm of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/59

Signed-off-by: 温差 <xushusheng.xss@antgroup.com>


* change vllm config
* .
 2025-03-25 11:26:52 +08:00
bowei.fw 89fb1a8009 Merge branch 'main' of code.alipay.com:inclusionAI/AReaL into async-ref-rew 2025-03-24 11:02:54 +08:00
bowei.fw 6547112a9d . 2025-03-24 11:02:40 +08:00
博惟 df90bb512a PullRequest: 55 Fix a recover bug caused by dataset filtering 
Merge branch fw/fix-recover20250322 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/55

Signed-off-by: 乘鹭 <hechuyi.hcy@antgroup.com>


* fix recover
 2025-03-22 22:54:14 +08:00
bowei.fw 0300f4b94b . 2025-03-22 14:58:19 +08:00
bowei.fw bd8df23a13 . 2025-03-22 14:57:12 +08:00
bowei.fw 88e99f887a . 2025-03-22 12:33:17 +08:00
bowei.fw 25c45c7e83 . 2025-03-22 12:22:34 +08:00
bowei.fw 9dcdb7a684 . 2025-03-21 22:38:21 +08:00
bowei.fw d1554585a4 Merge branch 'main' of code.alipay.com:inclusionAI/AReaL into async-ref-rew 2025-03-21 21:25:35 +08:00
bowei.fw de8243cc78 . 2025-03-21 21:22:50 +08:00
博惟 f90fe19e00 PullRequest: 53 Fix a potential reward hacking issue related to "emptyset" 
Merge branch fw/fix-rwd-hacking of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/53

Signed-off-by: 温差 <xushusheng.xss@antgroup.com>


* .
* .
 2025-03-21 16:42:24 +08:00
bowei.fw eb1e8a7592 dataset loading fixed 2025-03-20 21:52:01 +08:00
bowei.fw f8586e47c8 . 2025-03-20 15:24:31 +08:00
博惟 16e82698e0 PullRequest: 52 Fix ckpt ctl 
Merge branch fw/fix-save of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/52

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
* .
 2025-03-20 14:28:39 +08:00
博惟 86a4e69d0f PullRequest: 51 Fix a bug when ckpt_freq* are not set. 
Merge branch fw/fix-save of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/51

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
 2025-03-20 11:19:13 +08:00
博惟 5759579aa8 PullRequest: 48 Misc changes for supporting the async worker in the future 
Merge branch fw/async-worker of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/48

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
* .
* .
 2025-03-20 10:18:26 +08:00
Jun Mo 8732811c73 create ref-rw inference aysnc mode 2025-03-19 18:00:31 +08:00
博惟 b8f1fc3ebf PullRequest: 47 Add a filelock for NFS name resolve to avoid the concurrency issue. 
Merge branch fw/locked-nameresolve of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/47

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
 2025-03-19 16:31:23 +08:00
博惟 9c55827b32 PullRequest: 46 Call all runtime barriers upon CPU process groups and fix the SGLang performance with TP > 1 
Merge branch fw/fix-gpu-barrier of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/46?tab=diff

Signed-off-by: 闻通 <albert.zty@antgroup.com>


* .
 2025-03-19 16:29:31 +08:00
怀颉 9a9d86112e PullRequest: 45 fix: multiple model families 
Merge branch whj/fix-model-family of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/45

Signed-off-by: 博惟 <bowei.fw@antgroup.com>
 2025-03-18 15:46:45 +08:00
wanghuaijie.whj 8c592f8ca1 fix: multiple model families 2025-03-18 15:42:03 +08:00
晓雷 4ac9595295 PullRequest: 43 Reduce GPU memory used by data transfer. 
Merge branch mzy/fix-data-transfer-oom of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/43

Signed-off-by: 博惟 <bowei.fw@antgroup.com>


* add oom observe logs
* tested
* format and clear code
* .
* format
* remove logging
* .
* add comments
 2025-03-18 15:20:57 +08:00
君末 122bf6f214 PullRequest: 39 optimize code/math functioncall param 
Merge branch fix/math-code of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/39?tab=diff

Signed-off-by: 博惟 <bowei.fw@antgroup.com>
 2025-03-18 09:05:07 +08:00
Jun Mo 8310d7beb7 code format 2025-03-18 09:00:13 +08:00
博惟 b619f64cda PullRequest: 42 Fix the error raising logic and the bug when using sglang with tensor parallel 
Merge branch fw/patch20250317-3 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/42

Signed-off-by: 郭唯 <kira.gw@antgroup.com>


* .
 2025-03-17 20:37:43 +08:00
博惟 312e84b62c PullRequest: 41 fix typo 
Merge branch fw/patch20250317-2 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/41

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
 2025-03-17 17:00:04 +08:00
博惟 22548adf11 PullRequest: 40 Patch fix duplicated argument 
Merge branch fw/patch20250317 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/40

Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>


* .
 2025-03-17 16:53:54 +08:00
郭唯 583077c3d8 PullRequest: 32 Support profiling on ray 
Merge branch train-profiling of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/32

Signed-off-by: 博惟 <bowei.fw@antgroup.com>
 2025-03-17 16:13:07 +08:00
bowei.fw 843418ab42 format file 2025-03-17 16:12:49 +08:00