Skip to content

Issues: fla-org/flash-linear-attention

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

28 Open 105 Closed
28 Open 105 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Bug] AttributeError: module 'torch' has no attribute 'hip' bug Something isn't working
#207 opened Feb 28, 2025 by sozforex
2 tasks done
[Bug] Transformer Decoding: CUDA error: device-side assert triggered bug Something isn't working
#206 opened Feb 26, 2025 by HanGuo97
2 tasks
1
[Bug] Runtime error during Transformer model inference when use_cache=True bug Something isn't working
#204 opened Feb 26, 2025 by Lynn-020809
2 tasks done
[Feature Request] enhancement New feature or request
#203 opened Feb 26, 2025 by conceptofmind
7
[Bug] RWKV-7 with head size 64 crashes bug Something isn't working
#202 opened Feb 25, 2025 by johanwind
2 tasks done
5
[Bug] Triton error when running fused_recurrent_gsa_inference_kernel bug Something isn't working
#201 opened Feb 25, 2025 by Lynn-020809
2 tasks done
@yzhangcs
[Bug] RWKV-7 conversion results in subtly degraded performance, possibly due to numerical precision bug Something isn't working
#198 opened Feb 23, 2025 by Triang-jyed-driung
2 tasks done
6
[Bug] triton error when run chunk gated deltanet op bug Something isn't working
#196 opened Feb 21, 2025 by LouChao98
2 tasks done
@yzhangcs
5
Discrepancy on the hedgehog featmap implementation
#195 opened Feb 21, 2025 by LouChao98
[Bug] Fail to load RWKV7 model bug Something isn't working
#194 opened Feb 21, 2025 by sagejiaweili
2 tasks done
[RFC] Increase computation intensity for certain kernels enhancement New feature or request
#190 opened Feb 17, 2025 by sustcsonglin
1
[Bug] CUDA error: an illegal memory access was encountered (when using RWKV7Attention) bug Something isn't working
#186 opened Feb 16, 2025 by kyv001
2 tasks done
4
Questions about ops.ttt.naive.py
#185 opened Feb 14, 2025 by necrophagists
3
[RFC] enhanced evaluation support enhancement New feature or request
#184 opened Feb 13, 2025 by sustcsonglin
3
[Bug] dplr kernel causes core dumped bug Something isn't working
#173 opened Feb 8, 2025 by hypnopump
2 tasks done
1
[RFC] Fuse elementwise operations in RWKV layers enhancement New feature or request
#165 opened Feb 5, 2025 by sustcsonglin
2
[RFC] Support more hybrid patterns enhancement New feature or request urgent
#153 opened Feb 1, 2025 by sustcsonglin
[RFC] Implement model-specific 4d parallelism enhancement New feature or request
#148 opened Jan 28, 2025 by yzhangcs
1
[RFC] Fuse shortconv and output norm/gate into the kernel enhancement New feature or request
#140 opened Jan 24, 2025 by sustcsonglin FLA v1.0.0 release
@yzhangcs
[Bug] TypeError: 'constexpr' object is not iterable bug Something isn't working
#138 opened Jan 23, 2025 by York-Cheung
@yzhangcs
5
[RFC] Support for more finetuning Transformers to RNNs methods (e.g., LOLCATS) enhancement New feature or request urgent
#127 opened Jan 19, 2025 by sustcsonglin
[RFC] Autotune should consider batch size and number of heads enhancement New feature or request urgent
#117 opened Jan 11, 2025 by sustcsonglin FLA v1.0.0 release
2
[RFC] Remove head_first kernel enhancement New feature or request todo To be implemented
#114 opened Jan 10, 2025 by sustcsonglin FLA v1.0.0 release
[RFC] add Griffin and RecurrentGemma kernels enhancement New feature or request stale
#110 opened Jan 6, 2025 by sustcsonglin FLA v1.0.0 release
1
[RFC] Add xLSTM kernels enhancement New feature or request stale
#109 opened Jan 6, 2025 by sustcsonglin FLA v1.0.0 release
1
ProTip! Add no:assignee to see everything that’s not assigned.