Fix remaining f-string syntax errors
8f62d83
Andrew McCracken
Claude
commited on
Commit History
Fix f-string syntax error in streaming endpoint
c53e66f
Andrew McCracken
Claude
commited on
Add thread-safety for concurrent users
cfc97b4
Andrew McCracken
Claude
commited on
Configure uvicorn for concurrent request handling
6b0a701
Andrew McCracken
Claude
commited on
Add concurrent request handling with model pool
efd4459
Andrew McCracken
Claude
commited on
Revert to simpler configuration - optimizations caused slowdown
457c9e1
Andrew McCracken
Claude
commited on
Optimize for faster inference
8cfe5b7
Andrew McCracken
Claude
commited on
Optimize for 8vCPU/32GB instance
b7fb901
Andrew McCracken
Claude
commited on
Optimize model parameters for faster CPU inference
6e83384
Andrew McCracken
Claude
commited on
Fix: Force use of pre-built llama-cpp-python wheels
a922ca8
Andrew McCracken
commited on
Fix: Install llama-cpp-python at runtime (HF Spaces workaround)
3fad655
Andrew McCracken
commited on
Initial deployment to Spaces
2fb680d
Andrew McCracken
commited on