Logo
Explore Help
Register Sign In
fabolous005/prain
1
0
Fork 0
You've already forked prain
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
23 Commits 1 Branch 0 Tags
708e152549949bec86183123c50017b32fb89a8e
Commit Graph

4 Commits

Author SHA1 Message Date
fabolous005 708e152549 prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant 2026-10-28 22:07:25 +01:00
fabolous005 8b34961308 prain: stats planner and TOML writer 2026-10-27 13:52:06 +01:00
fabolous005 a5f011dcb8 prain: placement and option tables 2026-10-27 13:52:06 +01:00
fabolous005 db1736c42d prain: expert id ranges 2026-10-27 13:52:05 +01:00
Powered by Gitea Version: 1.26.4 Page: 15ms Template: 2ms
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