22 Commits
Author SHA1 Message Date
zefie 5265f78090 fix missing gguf-py 2026-11-04 22:06:45 -05:00
zefie 416b0e630f fix/improve hf to hf conversions 2026-11-04 21:43:53 -05:00
zefie cef832ecb0 update readme 2026-11-04 16:53:35 -05:00
zefie be97590146 add readme and fix docker.sh 2026-11-04 16:49:59 -05:00
zefie 3674fe921b update helper script 2026-11-04 16:44:06 -05:00
zefie 371d8792ba some fixes to Dockerfile 2026-11-04 16:41:04 -05:00
zefie 09ad871770 remove .vscode 2026-11-04 16:20:31 -05:00
zefie 0235fc7c82 remove .gitmodules 2026-11-04 16:19:42 -05:00
zefie e342fb2b81 fancy multi-stage Dockerfile, remove llama.cpp from repo, add zefie's local nvfp4_quant docker launcher helper 2026-11-04 16:12:01 -05:00
zefie db851967e1 create docker helper script 2026-11-04 16:09:22 -05:00
zefie 0ef586d131 add scripts/manpages for llama.cpp converters 2026-11-04 16:09:09 -05:00
zefie 66d47eea6a move from /root to /opt/nvfp4 2026-11-04 15:04:10 -05:00
zefie c67a729ac0 switch to llama.cpp submodule for up to date llama 2026-11-04 14:34:49 -05:00
zefie baa9c09e0e improve hf_to_nvfp4_safetensors 2026-11-04 14:30:11 -05:00
zefie b7ac8ed00c improve quant script with help of claude 2026-11-04 14:00:52 -05:00
zefie 95ce329879 fix docker 2026-11-03 17:58:52 -05:00
zefie b6037b3ea5 manfiles and new scripts 2026-11-03 15:23:48 -05:00
zefie 83566ee414 compile llama for the docker 2026-11-01 18:58:34 -05:00
zefie f1e394f1c9 improve quantization 2026-11-01 18:30:02 -05:00
zefie 0c49394911 some edits 2026-11-01 18:06:11 -05:00
zefie 8c66990853 include llama.cpp since there were some edits 2026-11-01 16:32:35 -05:00
zefie db7f28d087 initial commit 2026-11-01 16:31:33 -05:00