Files
ollama/cmd/launch
Jesse Gross f622b0c5fc launch: disable claude attribution header to preserve KV cache
Claude Code sends an x-anthropic-billing-header that changes on every
request. This is embedded in the system prompt and consequently
breaks the KV cache for every request. Given the size of the prompts
that Claude Code usees, this has significant performance impact.
2026-03-17 20:48:03 -07:00
..
2026-03-12 18:39:06 -07:00
2026-03-12 18:39:06 -07:00
2026-03-12 18:39:06 -07:00
2026-03-12 18:39:06 -07:00