Record straylight's new slot layout: four slots over one 262144-token pool
loopd's self-test caught the change (context per slot 131072 -> 262144, slots 2 -> 4). The device tests keep the expectation in one constant, and the M3a script matches it; verify-device passes 6 of 6 and the M3a device check passes. The inference contract notes which M0 findings rest on the old layout and need re-measuring. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -59,6 +59,13 @@ impl Drop for Proxy {
|
||||
}
|
||||
}
|
||||
|
||||
/// The server as deployed on straylight, recorded in one place. When the deployment changes on
|
||||
/// purpose, change this and `tools/check-m3a-device.sh` together, and note it in
|
||||
/// `docs/inference-contract.md`. Since 2026-09-22: four slots over one 262,144-token pool.
|
||||
const EXPECT: &str = r#"template_sha256 = "f55f52930aa8bf44ab5cb85f99370fcc3c56e9a85640b812086d5330bce5d86b"
|
||||
n_ctx = 262144
|
||||
slots = 4"#;
|
||||
|
||||
fn socket_path(name: &str) -> PathBuf {
|
||||
let dir = std::env::temp_dir().join(format!("loopd-device-{}-{name}", std::process::id()));
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
@@ -77,9 +84,7 @@ model = "{model}"
|
||||
main = 0
|
||||
background = 1
|
||||
[expect]
|
||||
template_sha256 = "f55f52930aa8bf44ab5cb85f99370fcc3c56e9a85640b812086d5330bce5d86b"
|
||||
n_ctx = 131072
|
||||
slots = 2
|
||||
{EXPECT}
|
||||
"#,
|
||||
socket.display()
|
||||
);
|
||||
@@ -253,9 +258,7 @@ model = "{model}"
|
||||
main = 0
|
||||
background = 1
|
||||
[expect]
|
||||
template_sha256 = "f55f52930aa8bf44ab5cb85f99370fcc3c56e9a85640b812086d5330bce5d86b"
|
||||
n_ctx = 131072
|
||||
slots = 2
|
||||
{EXPECT}
|
||||
[paths]
|
||||
home = "{}"
|
||||
"#,
|
||||
|
||||
Reference in New Issue
Block a user