Spaces:

vykanand
/

qwen2.5api

Sleeping

App Files Files Community

21 kB

Ctrl+K

Ctrl+K

1 contributor

History: 25 commits

vykanand's picture

Fix: lazy model load, GGUF integrity check, re-download corrupt files

9a8d0cd about 1 month ago

.gitattributes

1.52 kB
initial commit about 1 month ago
Dockerfile

738 Bytes
Fix: replace llama_cpp.server with custom FastAPI server (no mlock, no health check loop) about 1 month ago
README.md

515 Bytes
Production vLLM deploy: SHA-pinned Docker, pre-flight checks, ai.js client, usage guide about 1 month ago
ai.js

7.58 kB
Production vLLM deploy: SHA-pinned Docker, pre-flight checks, ai.js client, usage guide about 1 month ago
requirements.txt

108 Bytes
Fix: add uvicorn+fastapi deps (llama_cpp.server requires them) about 1 month ago
server.py

2.81 kB
Fix: lazy model load on first request, add error handling about 1 month ago
start.sh

984 Bytes
Fix: lazy model load, GGUF integrity check, re-download corrupt files about 1 month ago
usage.txt

6.76 kB
Production vLLM deploy: SHA-pinned Docker, pre-flight checks, ai.js client, usage guide about 1 month ago