biondizzle 487d960a6a D5c multi-tile: VERIFIED cos 0.999996 with Python KV merge + sink bias ...

Both segments (compressed+SWA with n_comp=96, and SWA-only with n_comp=0)
pass individually at cos 0.999996. The Python KV merge produces the
correct combined attention at cos 0.999996.

Key: n_comp is compile-time, so separate kernel instances are needed
for segments with different n_comp values. Production code would use
a kernel cache keyed on (n_comp, apply_sink_bias, ...).

2026-05-26 15:40:45 +00:00

..

e2e

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

integration

Restructure: cutedsl/ -> dsv4/ with proper layering

2026-05-21 17:30:44 +00:00

unit

D5c multi-tile: VERIFIED cos 0.999996 with Python KV merge + sink bias

2026-05-26 15:40:45 +00:00

check_log.sh

Add check_log.sh convenience script

2026-05-22 17:07:23 +00:00

requirements.txt

test: add standalone layer 0 comparison test (no vLLM, no Docker)

2026-05-16 02:13:18 +00:00

run_test.sh

run_test.sh: SIGKILL all children of screen session on cleanup

2026-05-22 17:08:12 +00:00

working_softmax_maybe.py

Clean up: archive diagnostics and superseded tests

2026-05-23 00:17:07 +00:00