Commit Graph

2206 Commits (e0c68ab6d3d64f401208d6ec66815995cee233c3)

Author SHA1 Message Date
duanjunwen e0c68ab6d3
[Zerobubble] merge main. (#6142)
5 days ago
ver217 184a653704 [checkpointio] fix pinned state dict
5 days ago
ver217 5fa657f0a1 [checkpointio] fix size compute
5 days ago
flybird11111 eb69e640e5 [async io]supoort async io (#6137)
5 days ago
Hongxin Liu b90835bd32 [checkpointio] fix performance issue (#6139)
5 days ago
Wang Binluo 8e08c27e19 [ckpt] Add async ckpt api (#6136)
5 days ago
Hongxin Liu d4a436051d [checkpointio] support async model save (#6131)
5 days ago
Hongxin Liu 5a03d2696d
[cli] support run as module option (#6135)
1 week ago
Hanks cc40fe0e6f
[fix] multi-node backward slowdown (#6134)
1 week ago
duanjunwen c2fe3137e2
[hotfix] fix flash attn window_size err (#6132)
1 week ago
Hongxin Liu a2596519fd
[zero] support extra dp (#6123)
2 weeks ago
Hongxin Liu a15ab139ad
[plugin] support get_grad_norm (#6115)
3 weeks ago
Hongxin Liu c2e8f61592
[checkpointio] fix hybrid plugin model save (#6106)
3 weeks ago
Hanks dee63cc5ef
Merge pull request #6096 from BurkeHulk/hotfix/lora_ckpt
1 month ago
BurkeHulk 6d6cafabe2 pre-commit fix
1 month ago
BurkeHulk b10339df7c fix lora ckpt save format (ColoTensor to Tensor)
1 month ago
Hongxin Liu 58d8b8a2dd
[misc] fit torch api upgradation and remove legecy import (#6093)
1 month ago
Hongxin Liu 5ddad486ca
[fp8] add fallback and make compile option configurable (#6092)
1 month ago
botbw 3b1d7d1ae8 [chore] refactor
1 month ago
botbw 2bcd0b6844 [ckpt] add safetensors util
1 month ago
Hongxin Liu cd61353bae
[pipeline] hotfix backward for multiple outputs (#6090)
1 month ago
Wenxuan Tan 62c13e7969
[Ring Attention] Improve comments (#6085)
1 month ago
Wang Binluo dcd41d0973
Merge pull request #6071 from wangbluo/ring_attention
1 month ago
wangbluo 83cf2f84fb fix
1 month ago
wangbluo bc7eeade33 fix
1 month ago
wangbluo fd92789af2 fix
1 month ago
wangbluo 6be9862aaf fix
1 month ago
wangbluo 3dc08c8a5a fix
1 month ago
wangbluo fe9208feac fix
1 month ago
wangbluo 3201377e94 fix
1 month ago
wangbluo 23199e34cc fix
1 month ago
wangbluo d891e50617 fix
1 month ago
wangbluo e1e86f9f1f fix
1 month ago
Tong Li 4c8e85ee0d
[Coati] Train DPO using PP (#6054)
1 month ago
wangbluo 1507a7528f fix
1 month ago
wangbluo 0002ae5956 fix
1 month ago
Hongxin Liu dc2cdaf3e8
[shardformer] optimize seq parallelism (#6086)
1 month ago
wangbluo efe3042bb2 fix
1 month ago
wangbluo 5ecc27e150 fix
1 month ago
wangbluo f98384aef6 fix
1 month ago
Hongxin Liu 646b3c5a90
[shardformer] fix linear 1d row and support uneven splits for fused qkv linear (#6084)
1 month ago
wangbluo b635dd0669 fix
2 months ago
wangbluo 3532f77b90 fix
2 months ago
wangbluo 3fab92166e fix
2 months ago
wangbluo 6705dad41b fix
2 months ago
wangbluo 91ed32c256 fix
2 months ago
wangbluo 6fb1322db1 fix
2 months ago
wangbluo 65c8297710 fix the attn
2 months ago
wangbluo cfd9eda628 fix the ring attn
2 months ago
botbw 4fa6b9509c
[moe] add parallel strategy for shared_expert && fix test for deepseek (#6063)
2 months ago