Spaces:

Electro0023
/

GGUF_MODEL

Sleeping

App Files Files Community

28.4 kB

Ctrl+K

Ctrl+K

3 contributors

History: 8 commits

Electro0023

Claude Opus 5

Document measured runtime on free CPU-basic

1f45ee1 22 days ago

.github
Robust OpenAI-compatible GGUF API: prebuilt CPU wheel, background model load, /v1/chat/completions about 1 month ago
.dockerignore

147 Bytes
Robust OpenAI-compatible GGUF API: prebuilt CPU wheel, background model load, /v1/chat/completions about 1 month ago
.gitignore

195 Bytes
Robust OpenAI-compatible GGUF API: prebuilt CPU wheel, background model load, /v1/chat/completions about 1 month ago
Dockerfile

1.34 kB
v2: Alpine base (musl wheels, no compile) + runtime model loading via POST /admin/load about 1 month ago
README.md

10.2 kB
Document measured runtime on free CPU-basic 22 days ago
main.py

10.7 kB
v3: serve vision (VLM) models alongside text, swappable at runtime 22 days ago
requirements.txt

532 Bytes
v2: Alpine base (musl wheels, no compile) + runtime model loading via POST /admin/load about 1 month ago
test_client.py

3.86 kB
v3: serve vision (VLM) models alongside text, swappable at runtime 22 days ago