indifferentketchup a8e475fdf4 perf(llama): unshadow cache-type + spec-decoding flags for agent opt-in ...

KV cache quantization (--cache-type-k q4_0) and ngram speculative decoding
(--spec-type ngram-mod) are high-value llama.cpp features that improve VRAM
usage and tokens/sec. Removing them from the shadowing lists allows agents
to enable them via llama_extra_args.

2026-06-07 22:40:23 +00:00

..

src

perf(llama): unshadow cache-type + spec-decoding flags for agent opt-in

2026-06-07 22:40:23 +00:00

CLAUDE.md

feat: deferred items — arena token API + UI, ToolShim docs

2026-06-07 18:41:26 +00:00

package.json

feat: single-source cross-app wire contracts in @boocode/contracts (v2.7.13)

2026-06-02 21:24:08 +00:00

tsconfig.json

v2.0.0-beta: write tools, pending-changes queue, inference loop, API routes

2026-05-25 01:53:38 +00:00

vitest.config.ts

test: vitest harness + unit tests for security-critical pure functions

2026-05-16 04:35:31 +00:00