Logo
Explore Help
Register Sign In
ywkang/kernbench2
1
0
Fork 0
You've already forked kernbench2
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
1971ac731c4027072df4c0ab46d48b7131dfe5de
kernbench2/tests/attention
T
History
eusonice 1971ac731c add three gqa attention kernel variants for short context length
2026-06-26 15:59:21 -07:00
..
test_gqa_decode_long_ctx_composite.py
feat(gqa): Case-6 composite-command decode variants + on-chip-operand DMA fix
2026-06-23 16:07:41 -07:00
test_gqa_decode_opt2.py
perf(cost-model): D8 single-op-cmd fast-path (FIXED=8 single-op / 40 composite)
2026-06-17 15:04:53 -07:00
test_gqa_prefill_compute_bound.py
paper(gqa): two-regime "use of composite commands" — decode + compute-bound prefill
2026-06-23 17:04:26 -07:00
test_gqa_short_context_sweep_decode.py
test short context length attention kernel
2026-06-26 15:59:21 -07:00
test_gqa_short_context_sweep_prefill.py
test short context length attention kernel
2026-06-26 15:59:21 -07:00
test_gqa_short_context.py
add three gqa attention kernel variants for short context length
2026-06-26 15:59:21 -07:00
test_milestone_gqa_decode_long_ctx_4cases.py
gqa: reorganize benches into gqa_helpers/ subpackage; drop legacy headline
2026-06-16 13:05:41 -07:00
test_milestone_gqa_prefill_long_ctx_4cases.py
gqa(prefill-4cases): add long-context prefill 4-cases comparative study
2026-06-16 13:06:08 -07:00
Powered by Gitea Version: 1.26.2 Page: 47ms Template: 3ms
Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API