Skip to content

Commit bdeedda

Browse files
Deploy: docs: GF16 paper draft — 16-bit format for ternary NN inference (#548)
- Format spec: 1/6/9 allocation, bias=31, u16 integer-backed - Results: 4x compression, BPB < 1.15, zero DSP utilization - Related work comparison: fp16, bfloat16, DLFloat - Trinity 3^k architecture context Refs #534
0 parents  commit bdeedda

1,028 files changed

Lines changed: 62389 additions & 0 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

.nojekyll

Whitespace-only changes.

CNAME

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
t27.ai

apple-touch-icon.png

6.55 KB
Loading

assets/BenchmarksSection-BTUGjqPB.js

Lines changed: 1 addition & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

assets/CalculatorSection-DJnE3i4Y.js

Lines changed: 1 addition & 0 deletions
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

0 commit comments

Comments
 (0)