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
1083aca9faf95a7449835b6e55a3997fd8be1c4c
CTI-Inference-Opt/代码/code
T
History
OwnerSunshine530 1083aca9fa feat: Triton BLOCK_M 可调(triton_block_m,默认64);bench --triton-bm 扫描
突破:triton评测39.92s/69.72(vs chunked 47.84/67.998)。继续调BLOCK_M榨。

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-17 13:01:50 +08:00
..
tests
feat: Triton varlen因果flash attention(块对角,单kernel,消逐块调用+mask构造开销)
2026-06-17 00:14:53 +08:00
bench.py
feat: Triton BLOCK_M 可调(triton_block_m,默认64);bench --triton-bm 扫描
2026-06-17 13:01:50 +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
feat: Triton BLOCK_M 可调(triton_block_m,默认64);bench --triton-bm 扫描
2026-06-17 13:01:50 +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: 259ms Template: 22ms
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