Spaces:

Leon4gr45
/

phi_inference

Sleeping

App Files Files Community

43.8 kB

Ctrl+K

Ctrl+K

1 contributor

History: 18 commits

Leon4gr45's picture

Document split KV quant + cache-reuse env vars

abde511 verified 1 day ago

__pycache__
port verified llama.cpp CPU proxy: LFM2.5-VL-1.6B vision via mmproj, native OpenAI multimodal API, prebuilt binary 3 days ago
.gitattributes

1.52 kB
initial commit 6 months ago
Dockerfile

1.72 kB
port verified llama.cpp CPU proxy: LFM2.5-VL-1.6B vision via mmproj, native OpenAI multimodal API, prebuilt binary 3 days ago
README.md

2.83 kB
Document split KV quant + cache-reuse env vars 1 day ago
app.py

16.3 kB
Split K/V cache quant, 16K ctx, cache-reuse, generation smoke test 1 day ago
requirements.txt

38 Bytes
port verified llama.cpp CPU proxy: LFM2.5-VL-1.6B vision via mmproj, native OpenAI multimodal API, prebuilt binary 3 days ago
test_vision.py

1.13 kB
port verified llama.cpp CPU proxy: LFM2.5-VL-1.6B vision via mmproj, native OpenAI multimodal API, prebuilt binary 3 days ago