transformers
[fix][wip] GlmMoeDsa: try implement DSA
#43912
Merged

[fix][wip] GlmMoeDsa: try implement DSA #43912

JaredforReal
JaredforReal init
73cf287e
JaredforReal JaredforReal requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 7 days ago
JaredforReal format
b4c0a929
JaredforReal
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-02-11
Rocketknight1
JaredforReal
ArthurZucker
ArthurZucker approved these changes on 2026-02-11
JaredforReal not indexer_rope_interleave
85c3bd1a
JaredforReal set MLA rope interleave to False
545d91ac
JaredforReal get rid of interleave in apply_rotary_pos_emb
6d0f6a87
JaredforReal Merge branch 'main' into glm-dsa
d829f860
JaredforReal reintroduce attention interface
e84b43c9
JaredforReal reset _cached_keys
558989a0
JaredforReal
HuggingFaceDocBuilderDev
ArthurZucker
ArthurZucker approved these changes on 2026-02-11
JaredforReal remove yarn
62454529
ArthurZucker fix tp plan for multi node runs
299c53c3
ArthurZucker support sdpa?
0d03c7de
ArthurZucker style
e06a41c7
ArthurZucker git push Merge branch 'main' of github.com:huggingface/transformers i…
dfcc43a1
ArthurZucker fix copies
f9c06d0b
ArthurZucker style
27fb77d4
ArthurZucker updates + skip some tests
430591ee
ArthurZucker skip some of the tests
5766920c
ArthurZucker skip some tests
9cad494f
ArthurZucker style and fix copies
7d5d14c4
ArthurZucker oups
56378050
github-actions
ArthurZucker style
aa4f19f8
ArthurZucker fml
ca7dfad7
ArthurZucker generate issues
a09945cf
ArthurZucker fix config
b54cf7b6
ArthurZucker :)
abd5ab08
ArthurZucker :) :) :) :)
dad15e77
ArthurZucker ArthurZucker enabled auto-merge (squash) 2 days ago
ArthurZucker FMLFMLFMLFMLF
4ca30213
disabled auto-merge 2 days ago
Manually disabled by user
ArthurZucker ArthurZucker merged a4a17617 into main 2 days ago
ArthurZucker
ArthurZucker commented on 2026-02-17

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone