wmantly aebc82e403 fix(proxy): handle client aborts and broken pipe disconnections gracefully without 500 errors

2026-09-16 00:34:14 +00:00

..

build-nccl-llama.sh

Initial commit: Complete deployment scripts, power governor, systemd units, and architecture documentation for Turing multi-GPU LLM rig

2026-09-01 01:55:19 +00:00

ollama-proxy.py

fix(proxy): handle client aborts and broken pipe disconnections gracefully without 500 errors

2026-09-16 00:34:14 +00:00

start-server.sh

feat(cache): enable radix prefix sharing, chunk cache reuse, and 32GB disk-backed slot persistence

2026-09-15 17:03:08 +00:00