Spaces:

innovatorved
/

llama-server

Sleeping

App Files Files Community

llama-server / Dockerfile

Commit History

Apply minimal safe perf wins for free-tier HF Space

cc953bd

Ved Gupta commited on Apr 26

Revert all perf tuning, restore working pre-tune config

509e3de

Ved Gupta commited on Apr 26

Revert KV-cache quant + force flash-attn defaults

62928db

Ved Gupta commited on Apr 26

Tune llama-server for faster CPU inference on HF free tier

f732b48

Ved Gupta commited on Apr 26

Initial commit: llama.cpp OpenAI-compatible server for Gemma 4 E2B

82bd3da

vedgupta commited on Apr 26