Repository Issue Activity (beta)

moonshotai/attention-residuals

Current issue state, recent activity, and per-issue timelines from the indexed issue data.

Open Issues
12
New in 7 Days
0
Closed in 7 Days
0
Average Open Age
167 days
Stale 30+ Days
12
Stale 90+ Days
10
Last 2 Weeks
DateOpenedClosedCommentsEventsOpen Backlog
2026-09-2000000
2026-09-19000012
2026-09-1800000
2026-09-1700000
2026-09-1600000
2026-09-1500000
2026-09-1400000
2026-09-1300000
2026-09-1200000
2026-09-1100000
2026-09-1000000
2026-09-0900000
2026-09-0800000
2026-09-0700000
This Week

Opened: 0

Closed: 0

Comments: 0

Events: 0

Top Labels

No label distribution is available yet.

Issue Explorer
IssueAuthorStateLabelsCommentsReactionsUpdated

#13 An implementation on Megatron

Opened 5 months ago
Smu-Tan
closed - completed
No labels
101 month ago

#14 Typo in the Block AttnRes block-partition description: L mod N should be corrected

Opened 1 month ago
chiamerica
open
No labels
001 month ago

#8 Talk is cheap. Show me the code.

Opened 6 months ago
poult-lab
open
No labels
3162 months ago

#4 这个方案可以和mHC结合使用吗?是否效果更优?

Opened 6 months ago
yuimo
open
No labels
304 months ago

#12 An implementation in Megatron-LM

Opened 5 months ago
Smu-Tan
open
No labels
015 months ago

#6 請問有實現的程式碼嗎?

Opened 6 months ago
ILoveSorasakiHina
open
No labels
495 months ago

#7 合影

Opened 6 months ago
Isdouer
open
No labels
425 months ago

#11 Proposal: Depth Routing Residuals (DRR) — An efficient extension of AttnRes with learned routing and block compression

Opened 6 months ago
Lockyd
open
No labels
215 months ago

#5 Release Kimi Linear AttnRes model on Hugging Face

Opened 6 months ago
NielsRogge
open
No labels
1136 months ago

#10 Featured Proposal:Supervisory Interface for Long-Horizon Interaction-Empirical Evidence from 180-Day LSO Trace

Opened 6 months ago
Flora-architecture
open
No labels
206 months ago

#3 为什么文章中完全没有任何参考引用?

Opened 6 months ago
yisar
open
No labels
436 months ago

#9 block parameter N

Opened 6 months ago
subneed
open
No labels
016 months ago

#2 Considering a different formulation

Opened 6 months ago
AssortedFantasy
open
No labels
006 months ago

#1 About the pipeline parallelism

Opened 6 months ago
JJJYmmm
closed - completed
No labels
106 months ago

Rows per page:

1–14 of 14