Logo
Explore Help
Register Sign In
Serendipity/CTI-Inference-Opt
1
1
Fork 0
You've already forked CTI-Inference-Opt
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
292a0216798dbf42f2f4b07d4d1258728127562f
CTI-Inference-Opt/代码/code
T
History
OwnerSunshine530 292a021679 experiment: triton_block_m=128(块数减半=launch减半);消同步赚-1.64s证评测对launch敏感→块大试
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-20 01:11:59 +08:00
..
tests
perf: _triton_block_meta 消除最后一个host同步(grid用shape派生上界,空block在kernel内mask空跑)
2026-06-19 20:51:37 +08:00
bench.py
feat: 真稀疏MoE(capacity分组,只算top-k,cutlass baddbmm,无host同步)
2026-06-17 21:05:55 +08:00
build_env.sh
fix: build_env.sh 简化为纯净版本(避免 CUDA 预热导致异常)
2026-06-12 21:55:09 +08:00
EXPERIMENTS.md
docs: 收尾 — 最终67.998/记录RepEncoder预计算尝试与结论
2026-06-16 13:18:48 +08:00
infer.py
experiment: triton_block_m=128(块数减半=launch减半);消同步赚-1.64s证评测对launch敏感→块大试
2026-06-20 01:11:59 +08:00
requirements.txt
revert: requirements.txt 还原为原始完整依赖列表
2026-06-12 21:24:22 +08:00
RISKS.md
docs: 潜在风险说明(RepEncoder预计算合规灰区/max_feasign一致性)与合规保底
2026-06-15 20:44:57 +08:00
Powered by Gitea Version: 26.3.1 Page: 945ms Template: 47ms
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