OpenNLPLab lightning-attention issues - Githubissues

OpenNLPLab / lightning-attention

Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models

MIT License

182 stars 15 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

question about benchmark

#13 Nalilik closed 4 months ago
2
Does using lightning-attention need retraining?

#12 ranpin closed 5 months ago
4
No-decay unusable

#11 jmercat closed 4 months ago
2
The methods for saving the Lightning-Attention model

#10 wsleepybear closed 6 months ago
1
The code stuck when running example_lightning_attn.py

#9 yang-yk closed 6 months ago
2
Tests fail

#8 catid closed 7 months ago
2
Add environment variable checks for BLOCK_SIZE and CBLOCK_SIZE

#7 relic-yuexi opened 7 months ago
1
Can the lightning_attn support V100?

#6 relic-yuexi closed 1 month ago
11
TypeError("unhashable type: 'tensor'")

#5 caihaihua057200 closed 4 months ago
7
When running lightning_attn_func two or more times, an error occurred.

#4 wsleepybear closed 7 months ago
10
assert d in supports_dim and e in supports_dim ?

#3 XintianHan opened 7 months ago
4
No module named 'lightning_attn'

#2 EddieEduardo closed 4 months ago
11
Cannot run the triton kernels

#1 jmercat closed 4 months ago
1