transformers
Refactor `MambaCache` to `modeling_mamba.py`
#38086
Merged

Refactor `MambaCache` to `modeling_mamba.py` #38086

manueldeprada merged 78 commits into huggingface:main from manueldeprada:main
manueldeprada
manueldeprada Refactor MambaCache to modeling_mamba.py (parity with Zamba)
1755d6fc
github-actions github-actions marked this pull request as draft 282 days ago
github-actions
manueldeprada ruff
93f7b8a8
manueldeprada Merge branch 'main' into main
be81dae0
manueldeprada fix dummies
dbdf2cce
manueldeprada manueldeprada marked this pull request as ready for review 282 days ago
github-actions github-actions requested a review from ArthurZucker ArthurZucker 282 days ago
github-actions github-actions requested a review from Rocketknight1 Rocketknight1 282 days ago
manueldeprada manueldeprada removed review request from Rocketknight1 Rocketknight1 282 days ago
manueldeprada manueldeprada removed review request from ArthurZucker ArthurZucker 282 days ago
HuggingFaceDocBuilderDev
manueldeprada manueldeprada requested a review from gante gante 282 days ago
manueldeprada update
1237dcc0
manueldeprada update
1b07f7f1
manueldeprada Merge branch 'main' into main
1ec3d4fd
gante
gante approved these changes on 2025-05-13
gante
manueldeprada remove mamba ref in cache tests
39e0edc5
manueldeprada remove cache_implementation from tests
09ffb0c8
manueldeprada Merge branch 'main' into main
d490d08f
manueldeprada
manueldeprada Merge branch 'main' of https://github.com/manueldeprada/transformers …
a9e445b7
huggingface huggingface deleted a comment from github-actions on 2025-05-14
manueldeprada
manueldeprada update
cae297ac
manueldeprada Merge remote-tracking branch 'upstream/main' into main
64541dcd
manueldeprada ruff
4b624dcd
manueldeprada ruff
b1987f87
manueldeprada Merge remote-tracking branch 'upstream/main' into main
a59fcfc0
gante
gante approved these changes on 2025-05-20
manueldeprada Merge branch 'main' into main
88f42f0c
manueldeprada Merge remote-tracking branch 'upstream/main' into main
72bb8b63
manueldeprada sneaky regression
9b867e50
manueldeprada Merge branch 'main' of https://github.com/manueldeprada/transformers …
e116efff
manueldeprada Merge remote-tracking branch 'upstream/main' into main
b3d5ec0b
manueldeprada model consistency
71786135
huggingface huggingface deleted a comment from github-actions on 2025-05-22
manueldeprada
gante
manueldeprada
gante
manueldeprada manueldeprada requested a review from ArthurZucker ArthurZucker 271 days ago
manueldeprada Merge remote-tracking branch 'upstream/main' into main
fbe8ec17
manueldeprada fix test_multi_gpu_data_parallel_forward
66b7162c
manueldeprada fix falcon slow tests
c9be2d97
manueldeprada ruff
4a630178
huggingface huggingface deleted a comment from github-actions on 2025-05-23
manueldeprada ruff
f7469a50
huggingface huggingface deleted a comment from github-actions on 2025-05-23
manueldeprada
manueldeprada add sample false
82e133fd
manueldeprada try to fix slow tests
819ad3f0
manueldeprada Revert "fix test_multi_gpu_data_parallel_forward"
511c17a8
manueldeprada fix tests on nvidia t4, remove dataparallel tests from mamba
143ee017
manueldeprada ruff
95af780e
manueldeprada remove DDP tests from mamba and falcon_mamba
57d84456
manueldeprada Merge branch 'main' into main
07e1e6f5
manueldeprada
huggingface huggingface deleted a comment from github-actions on 2025-05-26
huggingface huggingface deleted a comment from github-actions on 2025-05-26
huggingface huggingface deleted a comment from github-actions on 2025-05-26
huggingface huggingface deleted a comment from github-actions on 2025-05-26
github-actions
ArthurZucker
ArthurZucker commented on 2025-05-26
manueldeprada
manueldeprada add explicit error for MambaCache
3ca0398f
manueldeprada mamba2 also needs to init cache in prepare_inputs_for_generation
28a649ca
manueldeprada ruff
85553270
manueldeprada ruff
c623085d
manueldeprada Merge remote-tracking branch 'upstream/main' into main
60f04465
gante
manueldeprada Merge branch 'main' into main
9605ac94
manueldeprada move MambaCache to its own file
806ca0f0
manueldeprada ruff
cbd4eea0
manueldeprada unprotected import fix
e53a6100
manueldeprada
manueldeprada another attempt to fix unprotected imports
2338354f
manueldeprada Revert "another attempt to fix unprotected imports"
49fb04ba
manueldeprada fixing unprotected import, attempt 3
3cd32e04
manueldeprada
manueldeprada commented on 2025-05-26
manueldeprada
github-actions
manueldeprada manueldeprada requested a review from ArthurZucker ArthurZucker 267 days ago
manueldeprada
manueldeprada commented on 2025-06-02
manueldeprada Update src/transformers/cache_utils.py
52199d36
manueldeprada Merge branch 'main' into main
30c7b59f
manueldeprada ruff's fault
5f5febf9
manueldeprada
manueldeprada Merge remote-tracking branch 'upstream/main' into main
f1c8fb1f
manueldeprada Merge branch 'main' of github.com:huggingface/transformers into main
cc3f6b52
ArthurZucker
ArthurZucker requested changes on 2025-06-26
manueldeprada fix arthur review
bbdbbfcd
manueldeprada Merge branch 'main' of github.com:huggingface/transformers into main
6d8bd005
manueldeprada modular falcon mamba
0c3e7b3a
manueldeprada found a hack
67c8e494
manueldeprada fix config docs
8c65d298
manueldeprada fix docs
fea393f0
manueldeprada add export info
0182047c
manueldeprada Merge branch 'modular_falcon_mamba' into main
1887d539
manueldeprada merge modular falcon branch
59be6d6f
manueldeprada Merge branch 'main' into main
2477ebbf
manueldeprada manueldeprada requested a review from ArthurZucker ArthurZucker 237 days ago
manueldeprada oopsie
abb9cd37
manueldeprada Merge branch 'main' of https://github.com/manueldeprada/transformers …
203f103d
manueldeprada Merge branch 'main' into main
1ec801cb
manueldeprada Merge branch 'main' into main
cb21911f
manueldeprada Merge branch 'main' into main
a1044bb4
ArthurZucker
ArthurZucker commented on 2025-07-15
manueldeprada fix fast path failing
19d7018a
manueldeprada new approach
80b1cf16
manueldeprada oopsie
98cdaabf
manueldeprada fix types
339f63a0
manueldeprada Merge branch 'main' of github.com:huggingface/transformers into main
1f8b6374
manueldeprada Merge branch 'main' of github.com:huggingface/transformers into main
2ffeafd2
manueldeprada manueldeprada changed the title Refactor `MambaCache` to `modeling_mamba.py` (parity with Zamba) Refactor `MambaCache` to `modeling_mamba.py` 217 days ago
manueldeprada
manueldeprada commented on 2025-07-16
ArthurZucker
ArthurZucker commented on 2025-07-17
manueldeprada Revert new pragma in modular
29639922
manueldeprada trying another modular workaround
f4776e42
manueldeprada review & fix ci
b56321fc
manueldeprada Merge branch 'main' of github.com:huggingface/transformers into main
6a76b057
manueldeprada oopsie
bfb8470b
manueldeprada
manueldeprada commented on 2025-07-17
manueldeprada
manueldeprada commented on 2025-07-17
ArthurZucker
ArthurZucker commented on 2025-07-21
manueldeprada clear prepare_inputs on mamba/mamba2/falcon_mamba
13065947
github-actions
manueldeprada
ArthurZucker
ArthurZucker approved these changes on 2025-07-21
manueldeprada manueldeprada merged 1aa7256f into main 212 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone