Home/LLM Frameworks/long-context-attention
long-context-attention logo

long-context-attention

Enrichment pending
feifeibear/long-context-attention

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference

GraphCanon updated today · GitHub synced today

678
Stars
80
Forks
12
Open issues
5
Watchers
1mo
Last push
Python Apache-2.0Created Mar 27, 2024

Trust & integrity

Full report
Maintenance
Steady (51d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Personal account
As of today · Source: github_public_v1
Security (OSV)
No lockfile
As of today · Source: none

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

USP: Unified (a.k.a. Hybrid, 2D) Sequence Parallel Attention for Long Context Transformers Model Training and Inference