Commit graph

62 commits

Author SHA1 Message Date
Jai Suphavadeeprasit
d2ea8cd612 remove KL 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
90281f5993 lora restart saving gradient changes 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
eb123f9596 ditching lora nccl 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
c33f9170c3 nccl loras 2026-03-02 11:18:52 -05:00
pre-commit-ci[bot]
5cfd1929f1 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
238602e855 linting 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
04f2850980 python versioning problems 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
672cdbaea8 cleanup 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
6833d4d820 major refactor 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
58a3fb8b14 pipelineRL 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
be16a2914d testing scripts 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
29327c0605 hot swap adapter 2026-03-02 11:18:52 -05:00
pre-commit-ci[bot]
d288456535 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
3f69da5248 LORA 1 2026-03-02 11:18:52 -05:00
pre-commit-ci[bot]
3517d07c8a [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
412aaef2ba linter 2026-03-02 11:18:52 -05:00
pre-commit-ci[bot]
e6e0691bd7 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
f87455a712 keep debugging flags for future use 2026-03-02 11:18:52 -05:00
pre-commit-ci[bot]
d4589e1107 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
f57ef091aa readme updates 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
23b6552277 vllm weight bridge 2026-03-02 11:18:52 -05:00
pre-commit-ci[bot]
fe2fd3d824 [pre-commit.ci] auto fixes from pre-commit.com hooks
for more information, see https://pre-commit.ci
2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
4740dfa216 single copy now working as expected 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
fc65546f8d prints 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
2384ab3dcd clean up 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
906802299c fused memory 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
9a95ec5aa1 other changes 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
6efec3f1c5 adjusting buffers 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
a92c935fba buffer efficiency 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
5bba112244 debugging 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
1f79e86ba0 pass all the informaiton 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
96871e0724 unsure 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
17e93cbda4 main changes 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
e2006b4015 pipeline changes 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
df3651990d streamline process 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
d3ef94ef11 serialization errors 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
fcd426e934 single copy 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
fad8e77be2 patching problem 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
80d2608c4e basic changes 2026-03-02 11:18:52 -05:00
Jai Suphavadeeprasit
14ebf7a492 changes 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
5640d7de25 error handling 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
ff8eaf9e3c param locations update 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
27b122a415 changes based on torchtitan 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
533f0bf286 IPC updates 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
78ea8bc3e7 health changes 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
3b469f2445 add missing parameter 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
689055f0ec standardize the training approach 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
b1b9943473 tracking 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
e4fc514763 training bug 2026-03-02 11:18:51 -05:00
Jai Suphavadeeprasit
c336d981ce smol changes 2026-03-02 11:18:51 -05:00