Default Branch

b1915d2889 · Merge pull request #6391 from hpcaitech/grpo-zero-bubble-rebase · Updated 2025-11-13 01:54:34 +00:00

Branches

16169d1f22 · Revert "[feat] Update reward verification" · Updated 2025-05-06 04:59:30 +00:00

175
54

4d18e7d772 · spot a possible bug · Updated 2025-05-05 10:48:42 +00:00

175
59

d4a6b6c4a7 · update evaluation parameters · Updated 2025-05-04 08:41:27 +00:00

175
57

d06042b434 · rewrite reward fn · Updated 2025-05-01 03:28:05 +00:00

175
52

87bac841ea · Merge pull request #6288 from duanjunwen/support_hybrid_model_sync · Updated 2025-04-29 10:22:32 +00:00

175
49

93b40e888f · Merge branch 'grpo-latest' of https://github.com/hpcaitech/ColossalAI into grpo-dev · Updated 2025-04-29 09:07:27 +00:00

175
54

56e4e74140 · boxed version · Updated 2025-04-23 09:20:09 +00:00

175
42

7bb7e80476 · [feat] GRPO with distributed implementation (#6230) · Updated 2025-04-21 02:43:49 +00:00

175
4

6e096362ef · [pre-commit.ci] auto fixes from pre-commit.com hooks · Updated 2025-03-07 10:43:03 +00:00

175
22

44d4053fec · [HotFix] update load lora model Readme; (#6240) · Updated 2025-03-07 06:14:26 +00:00

167
0
Included

f736d747e3 · update grpo · Updated 2025-02-25 10:12:04 +00:00

175
5

f32861ccc5 · [misc] update torch version (#6206) · Updated 2025-02-24 06:35:48 +00:00

170
0
Included

97e60cbbcb · [checkpointio] gather tensor before unpad it if the tensor is both padded and distributed (#6168) · Updated 2025-01-21 02:23:15 +00:00

189
0
Included

d6af7be06e · fix · Updated 2024-11-25 09:12:29 +00:00

207
13

64f74a157e · [NPU]support npu (#6089) · Updated 2024-11-20 07:28:35 +00:00

269
1

810cafb2f9 · Merge pull request #6114 from duanjunwen/dev/zero_bubble · Updated 2024-11-18 09:38:49 +00:00

227
130

a2596519fd · [zero] support extra dp (#6123) · Updated 2024-11-12 03:20:46 +00:00

222
0
Included

bcbd311bc3 · Update README.md · Updated 2024-10-10 08:52:55 +00:00

272
1

3568df498a · [pre-commit.ci] auto fixes from pre-commit.com hooks · Updated 2024-08-23 05:50:37 +00:00

316
1

f7b4fb5f07 · [pre-commit.ci] auto fixes from pre-commit.com hooks · Updated 2024-08-12 03:12:23 +00:00

400
4