Harvesting forks from GitHub — first visit takes a few seconds…
DevedseOrg/beellama.cpp
DFlash & TurboQuant in llama.cpp with up to 3x faster generation and 7.5x more KV cache in same VRAM
0 commentsView comments →
No comments yet. Be the first.
Top forks by stars
unchangedC++
DFlash & TurboQuant in llama.cpp with up to 3x faster generation and 7.5x more KV cache in same VRAM
View on GitHub ↗
Comments (0)