Ilker ManapandClaude Opus 5.5
481523ca46
A --context-length 32768 --ctx-pool 32768 model got llama.cpp's default four slots of 8192, and refused what the gateway admitted; --parallel is now what the pool holds of the context. max_output was 1024 for every model, which cut an editor's agent off mid-file; it is now a quarter of the context, from 1024 to 8192. --tools writes capabilities.tools, which the Continue configuration now reads, as it reads max_output. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
32 lines
1003 B
Go
32 lines
1003 B
Go
package modelserve
|
|
|
|
import (
|
|
"slices"
|
|
"testing"
|
|
)
|
|
|
|
func TestLlamaCppIsGivenTheSlotsTheCatalogPromises(t *testing.T) {
|
|
// A 32768 pool for 32768-token requests is one slot: the engine's own
|
|
// four made slots of 8192, and requests the gateway admitted were refused.
|
|
for _, c := range []struct {
|
|
pool, ctx int
|
|
want []string
|
|
}{
|
|
{32768, 32768, []string{"--ctx-size", "32768", "--parallel", "1"}},
|
|
{16384, 4096, []string{"--ctx-size", "16384", "--parallel", "4"}},
|
|
{65536, 16384, []string{"--ctx-size", "65536", "--parallel", "4"}},
|
|
} {
|
|
if got := llamaArgs(Request{CtxPool: c.pool, ContextLength: c.ctx}); !slices.Equal(got, c.want) {
|
|
t.Errorf("pool %d, context %d: %v", c.pool, c.ctx, got)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestTheLongestAnswerGrowsWithTheContext(t *testing.T) {
|
|
for ctx, want := range map[int]int{2048: 1024, 4096: 1024, 16384: 4096, 32768: 8192, 131072: 8192} {
|
|
if got := maxOutput(ctx); got != want {
|
|
t.Errorf("context %d: max output %d, want %d", ctx, got, want)
|
|
}
|
|
}
|
|
}
|