3 people 8c9e7a1514 docs: decode speed status report — 0.84x q8_0, experiment branch was net negative ...

Main branch at 65.8 decode tok/s (0.84x q8_0). Experiment branch
with custom GGML_OP_TURBO_WHT dropped to 61.5 (-6.5%, net negative).
Root cause: centroid LUT is 100% of the gap (verified with speed ceiling test).
All attempted LUT optimizations either marginal or regressive.

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

2026-03-25 21:34:05 -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: decode speed status report — 0.84x q8_0, experiment branch was net negative

2026-03-25 21:34:05 -05:00

experiment-context-scaling-fix.md

docs: group-32 rotation failed (PPL 7.06)

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

pre-rotate-queries-investigation.md

docs: move engineering docs here from llama.cpp fork

2026-03-25 16:16:58 -05:00

pre-rotate-queries-plan.md

docs: move engineering docs here from llama.cpp fork

2026-03-25 16:16:58 -05:00

quality-benchmarks.md

docs: update all docs with q8_0 parity results (2747 tok/s, 4.6x compression)

2026-03-25 18:01:14 -05:00

speed-experiments.md

docs: block-32 breakthrough — q8_0 parity at 4.6x compression

2026-03-25 17:34:27 -05:00

turbo-speed-investigation.md

docs: update all docs with q8_0 parity results (2747 tok/s, 4.6x compression)

2026-03-25 18:01:14 -05:00

turboquant-plus-experiments.md

docs: TurboQuant+ experiments master document — status, findings, dead ends

2026-03-25 20:49:49 -05:00