Spaces:
Sleeping
Sleeping
Commit History
-
Cache causal mask for faster inference
Verified signature89ad9ef
-
Fix completion_tokens: count tokens not decoded characters
Verified signature80c1b86
-
Switch to HTTP.serve (non-streaming handler) for proxy compatibility
Verified signatured353df1 -
Fix: add Content-Length for non-streaming responses, X-Accel-Buffering for SSE
Verified signature6c7eeb4 -
Upload server.jl with huggingface_hub
Verified signature10ad6b5 -
Upload folder using huggingface_hub
Verified signature18db312 -
initial commit
Verified signature4b77973