github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-05-06 15:38:26 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,809 Commits 46 Branches 49 Tags 233 MiB

Default Branch

main

46ed5d856b · [ci] update ci () · Updated 2025-04-18 08:40:53 +00:00

Branches

revert-6292-grpo-latest-dev-reward-update

16169d1f22 · Revert "[feat] Update reward verification" · Updated 2025-05-06 04:59:30 +00:00
10
54
pre-commit-ci-update-config

3ffb312802 · [pre-commit.ci] auto fixes from pre-commit.com hooks · Updated 2025-05-05 17:23:25 +00:00
0
2
grpo-latest-dev-debug

4d18e7d772 · spot a possible bug · Updated 2025-05-05 10:48:42 +00:00
10
59
grpo-latest-v3

d4a6b6c4a7 · update evaluation parameters · Updated 2025-05-04 08:41:27 +00:00
10
57
grpo-latest

17928ad84f · Merge pull request from hpcaitech/grpo-latest-dev-reward-update · Updated 2025-05-03 02:00:32 +00:00
10
53
grpo-latest-dev-reward-update

d06042b434 · rewrite reward fn · Updated 2025-05-01 03:28:05 +00:00
10
52
grpo-latest-dev

01640ebd65 · fix bug · Updated 2025-04-30 14:53:12 +00:00
10
50
feat/hybrid_model_sync

87bac841ea · Merge pull request from duanjunwen/support_hybrid_model_sync · Updated 2025-04-29 10:22:32 +00:00
10
49
grpo-dev

93b40e888f · Merge branch 'grpo-latest' of https://github.com/hpcaitech/ColossalAI into grpo-dev · Updated 2025-04-29 09:07:27 +00:00
10
54
upgrade_transformers

8497ecc3e5 · Merge pull request from flybird11111/upgrade-transformers · Updated 2025-04-24 09:30:40 +00:00
0
55
feat/boxed-version

56e4e74140 · boxed version · Updated 2025-04-23 09:20:09 +00:00
10
42
feature/ray-rlhf

7bb7e80476 · [feat] GRPO with distributed implementation () · Updated 2025-04-21 02:43:49 +00:00
10
4
deep_gemm

b42472859a · Allow to compute when bsz == 1 · Updated 2025-03-19 08:07:39 +00:00
2
4
feat/ppo

6e096362ef · [pre-commit.ci] auto fixes from pre-commit.com hooks · Updated 2025-03-07 10:43:03 +00:00
10
22
uxsqN94oMfWTUNCA

44d4053fec · [HotFix] update load lora model Readme; () · Updated 2025-03-07 06:14:26 +00:00
2
0
 Included
feat/grpo

f736d747e3 · update grpo · Updated 2025-02-25 10:12:04 +00:00
10
5
feature/dualpipe

f32861ccc5 · [misc] update torch version () · Updated 2025-02-24 06:35:48 +00:00
5
0
 Included
feature/dist-ckp-io

97e60cbbcb · [checkpointio] gather tensor before unpad it if the tensor is both padded and distributed () · Updated 2025-01-21 02:23:15 +00:00
24
0
 Included
ckpt_api

d6af7be06e · fix · Updated 2024-11-25 09:12:29 +00:00
42
13
support-npu

64f74a157e · [NPU]support npu () · Updated 2024-11-20 07:28:35 +00:00
104
1