frank-default-small: KV K default f16 (no hadamard), V q6_0 + hadamard
K cache back to default f16 full precision with K_CACHE_HADAMARD=0; V cache at q6_0 with V_CACHE_HADAMARD=1. Env, serve script, bats, and KB updated.
This commit is contained in:
@@ -20,10 +20,11 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
|
||||
grep -q '163840 per slot' "$ENV_FILE"
|
||||
}
|
||||
|
||||
@test "frank-default-small uses K q8_0 + V q5_0 KV cache with Hadamard" {
|
||||
grep -q '^CACHE_TYPE_K=q8_0$' "$ENV_FILE"
|
||||
grep -q '^CACHE_TYPE_V=q5_0$' "$ENV_FILE"
|
||||
grep -q '^K_CACHE_HADAMARD=1$' "$ENV_FILE"
|
||||
@test "frank-default-small uses default f16 K and q6_0 V KV cache" {
|
||||
grep -q '^CACHE_TYPE_K=f16$' "$ENV_FILE"
|
||||
grep -q '^CACHE_TYPE_V=q6_0$' "$ENV_FILE"
|
||||
# K at default f16 has no Hadamard; V at q6_0 keeps Hadamard.
|
||||
grep -q '^K_CACHE_HADAMARD=0$' "$ENV_FILE"
|
||||
grep -q '^V_CACHE_HADAMARD=1$' "$ENV_FILE"
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user