6547112a9d
.
2025-03-24 11:02:40 +08:00
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
0300f4b94b
.
2025-03-22 14:58:19 +08:00
bd8df23a13
.
2025-03-22 14:57:12 +08:00
88e99f887a
.
2025-03-22 12:33:17 +08:00
25c45c7e83
.
2025-03-22 12:22:34 +08:00
9dcdb7a684
.
2025-03-21 22:38:21 +08:00
d1554585a4
Merge branch 'main' of code.alipay.com:inclusionAI/AReaL into async-ref-rew
2025-03-21 21:25:35 +08:00
de8243cc78
.
2025-03-21 21:22:50 +08:00
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
eb1e8a7592
dataset loading fixed
2025-03-20 21:52:01 +08:00
f8586e47c8
.
2025-03-20 15:24:31 +08:00
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
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
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
8732811c73
create ref-rw inference aysnc mode
2025-03-19 18:00:31 +08:00
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
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
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
8c592f8ca1
fix: multiple model families
2025-03-18 15:42:03 +08:00
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
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
8310d7beb7
code format
2025-03-18 09:00:13 +08:00
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
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
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
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
843418ab42
format file
2025-03-17 16:12:49 +08:00
92e0777178
optimize code/math functioncall param
2025-03-17 15:45:52 +08:00
767bb7bf47
PullRequest: 38 Support SGLang generation based on the 24.07 docker image
...
Merge branch fw/sglang of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/38?tab=comment#note_168700036
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
* .
* .
* .
* .
* .
* format
* .
* .
* cleanup
2025-03-17 15:45:00 +08:00
7b3e33430a
PullRequest: 37 Support Megatron v0.9.0
...
Merge branch fw/megatron-v0.9.0 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/37
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
* .
* .
* .
* .
* .
* format
2025-03-17 14:49:26 +08:00
69681d9fe4
PullRequest: 35 Support log probability recomputation in PPO.
...
Merge branch fw/recompute-logprob of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/35
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
* .
* .
* .
* .
2025-03-17 14:38:53 +08:00
c074d6142b
PullRequest: 36 Fix SLURM singularity environments on PPU cluster
...
Merge branch mzy/fix-ppu-no-home of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/36
Signed-off-by: 博惟 <bowei.fw@antgroup.com>
* .
2025-03-17 12:33:03 +08:00
17a4ada06e
PullRequest: 33 Force the partition to be balanced when the capacity is a large number
...
Merge branch fw/balanced-pack of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/33
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
Signed-off-by: 步偶 <sam.gjx@antgroup.com>
* .
2025-03-17 10:47:29 +08:00
0b15ead835
PullRequest: 34 Fix the fp16 training issue.
...
Merge branch fw/fix-fp16 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/34
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
Signed-off-by: 步偶 <sam.gjx@antgroup.com>
* fix bf16 training issue
2025-03-17 10:46:57 +08:00
548aaef642
PullRequest: 22 避免log_softmax时出现OOM的问题
...
Merge branch ranghou-math of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/22?tab=comment#note_168300024
Signed-off-by: 博惟 <bowei.fw@antgroup.com>
2025-03-14 11:21:42 +08:00
d70586f85e
memory saving for log_softmax and gather
2025-03-14 10:18:28 +08:00
07e724741b
Support profiling on ray
2025-03-13 11:40:37 +08:00
234e3dd3a0
PullRequest: 31 Fix typo in topology name
...
Merge branch fw/topo of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/31
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
* change non-training topo order
* .
* fix the dataloading bug during recover
* fix typo
* fix typo
2025-03-12 18:31:18 +08:00
56e4dd1f5d
PullRequest: 30 Change the topology order of vLLM for better locality of pipeline parallelism
...
Merge branch fw/topo of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/30?tab=comment
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
* change non-training topo order
* .
* fix the dataloading bug during recover
* fix typo
2025-03-12 17:26:50 +08:00
3d8be914af
PullRequest: 20 Fix bugs in auto evaluation
...
Merge branch mzy/refactor-eval of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/20?tab=diff
Signed-off-by: 博惟 <bowei.fw@antgroup.com>
* test
* move evaluator to main process
* .
* clear codes
* add docstring
* .
* separate wandb groups
* .
* handle eval error
* add check for failed eval
* refactor evaluator
* refactor evaluator, fix master worker wandb login
* .
2025-03-12 16:10:12 +08:00
26a48be73e
PullRequest: 29 fix the dataloading bug during recover
...
Merge branch fw/fix-recover-dataloading of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/29
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
* fix the dataloading bug during recover
2025-03-12 16:00:49 +08:00
fb23009e99
PullRequest: 27 support bf16 training
...
Merge branch fw/bf16 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/27
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
* support bf16 training
2025-03-12 13:04:30 +08:00
9a07ab9460
PullRequest: 28 Fix a dataloading bug
...
Merge branch fw/patch20250312 of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/28
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
* fix dataloading bug
2025-03-12 13:04:15 +08:00
cdf13ff852
PullRequest: 26 Set functioncall disabled by default for opensource
...
Merge branch fix/math of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/26
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
2025-03-11 19:39:31 +08:00
6fd0db01c7
add functioncall switch
2025-03-11 18:41:46 +08:00
480f0ef502
PullRequest: 25 fix the save version in rw interface
...
Merge branch rw_save_version of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/25
Signed-off-by: 博惟 <bowei.fw@antgroup.com>
* fix the save version in rw interface
* format
2025-03-11 16:30:03 +08:00
ffe1cd71ea
PullRequest: 23 Fix a problem about singularity environments on SLURM
...
Merge branch mzy/fix-slurm of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/23
Signed-off-by: 博惟 <bowei.fw@antgroup.com>
* fix slurm + singularity environment
2025-03-10 20:31:57 +08:00
32b92a08f9
PullRequest: 21 fix timeutil consistency during recover
...
Merge branch fw/fix-timeutil-recover of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/21
Signed-off-by: 步偶 <sam.gjx@antgroup.com>
* fix timeutil consistency during recover
2025-03-10 16:27:55 +08:00
e968ac47eb
PullRequest: 19 Fix training time of 7B in README
...
Merge branch fix-tutorials of git@code.alipay.com:inclusionAI/AReaL.git into main
https://code.alipay.com/inclusionAI/AReaL/pull_requests/19
Signed-off-by: 晓雷 <meizhiyu.mzy@antgroup.com>
2025-03-08 18:35:47 +08:00
bowei.fw