-
Notifications
You must be signed in to change notification settings - Fork 1.8k
Pull requests: state-spaces/mamba
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix layer_norm backward to reuse the forward dropout mask and scale dx1 by rowscale
#1023
opened Aug 25, 2026 by
cyboTiger
Loading…
mamba3: access ctx.saved_tensors exactly once in backward
#1021
opened Aug 18, 2026 by
jgcb00
Loading…
Sequences longer than ~61K tokens (and often less) silently give a wrong answer or crash
#1016
opened Aug 12, 2026 by
chipsncheese-ie
Loading…
Add an opt-in Helion kernel backend for the Mamba-2 SSD path
#1012
opened Aug 3, 2026 by
shcho1118
Loading…
fix: apply min-p filtering on softmax probabilities
#1010
opened Jul 31, 2026 by
Chessing234
Contributor
Loading…
2 tasks
fix: MambaLMHeadModel and create_block robustness
#1008
opened Jul 31, 2026 by
Chessing234
Contributor
Loading…
1 of 2 tasks
test: MambaConfig and varlen helper regression coverage
#1009
opened Jul 31, 2026 by
Chessing234
Contributor
Loading…
1 task done
fix: harden Hugging Face config/weight loading helpers
#1007
opened Jul 31, 2026 by
Chessing234
Contributor
Loading…
1 task done
fix: harden setup.py CUDA build guards and wheel fallback messaging
#1004
opened Jul 31, 2026 by
Chessing234
Contributor
Loading…
1 of 2 tasks
ci: publish wheels for torch 2.11, 2.12.1, and 2.13.0
#1005
opened Jul 31, 2026 by
Chessing234
Contributor
Loading…
1 of 2 tasks
[
Triton] Fix triton launch grids under multi gpu scenarios
#1003
opened Jul 30, 2026 by
vasqu
Contributor
Loading…
Build C++/CUDA extensions with -std=c++20 (torch 2.14 ATen requires C++20)
#1000
opened Jul 24, 2026 by
atalman
Loading…
Fix numerical instability in A_log during training (closes #72)
#996
opened Jul 22, 2026 by
KakashiTech
Loading…
fix: pin apache-tvm-ffi below 0.1.10 for tilelang 0.1.8
#995
opened Jul 18, 2026 by
Chessing234
Contributor
Loading…
2 tasks
fix: force TileLang-contiguous inputs for Mamba3 MIMO
#994
opened Jul 18, 2026 by
Chessing234
Contributor
Loading…
1 task
fix: honor dtype/device in load_state_dict_hf
#993
opened Jul 17, 2026 by
Chessing234
Contributor
Loading…
1 task
Fix Mamba2.step() D handling when D_has_hdim=True
#981
opened Jun 24, 2026 by
Chessing234
Contributor
Loading…
2 tasks
fix: cast x buffer offset to int64 to prevent int32 overflow
#980
opened Jun 24, 2026 by
Chessing234
Contributor
Loading…
4 tasks
Fix Mamba2.step() D skip when D_has_hdim=True
#979
opened Jun 24, 2026 by
Chessing234
Contributor
Loading…
Fix Mamba-3 decode path: forward() to step() shape handling
#978
opened Jun 20, 2026 by
sanowl
Loading…
Add support for input states to Mamba-3 forward pass
#976
opened Jun 15, 2026 by
aakashlahoti
Collaborator
Loading…
Installation and Build Failure on Modern Cloud Environments (Python 3…
#975
opened Jun 14, 2026 by
Turusore08
Loading…
Add
state_batch_indices to mamba3_step_fn (paged-inference state pools, parity with selective_state_update)
#971
opened Jun 11, 2026 by
jgcb00
Loading…
Remove host syncs from
compute_dacs_segsum_triton_varlen
#969
opened Jun 11, 2026 by
jgcb00
Loading…
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.