turboquant_plus

starred/turboquant_plus

0 Fork 0

mirror of https://github.com/TheTom/turboquant_plus.git synced 2026-10-22 11:02:42 -05:00

Files

T

History

ebad090702 docs: update comparison matrix with 10 community testers from X post

New pending testers: @spiritbuun (3090 CUDA, fixed dequant), @jxwalker
(2x3090 NVLink), @vaiduakhu (5090), @MyopicRaccoon (3090 Thunderbolt),
@JamesNumb3rs (9070 RDNA4), @DarkSmak812 (6800XT RDNA2/ROCm).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: tturney@psyguard.ai

2026-03-26 12:03:57 -05:00

context-scaling-deep-dive.md

docs: extended context scaling verified — 0.99x q8_0 through 32K context

2026-03-25 20:21:22 -05:00

decode-speed-status.md

docs: Mario PDF test confirms decode scaling — 0.66x q8_0 at 48K context

2026-03-25 22:08:23 -05:00

experiment-context-scaling-fix.md

docs: group-32 rotation failed (PPL 7.06)

2026-03-25 19:31:11 -05:00

experiment-layer-adaptive-extended.md

docs: layer-adaptive mode 2 verified 2K-32K — q8_0 quality at 3.5x compression