|
|
@@ -63,7 +63,7 @@ args = [
|
|
|
# DCP4 (2026-10-22, third boot): context is sharded across the 4 ranks, so
|
|
|
# 8 GiB/rank pins ~32 GiB aggregate — one 524288-token request needs ~27 GiB
|
|
|
# aggregate (51.6 KB/token/rank unsharded, measured), which just fits.
|
|
|
- "--kv-cache-memory-bytes", "6442450944",
|
|
|
+ "--kv-cache-memory-bytes", "8053063680",
|
|
|
# Decode-context parallelism: the proven r35 4x shape for the Flash sibling
|
|
|
# (glm53-flash-r35-4x-dcp4). Unverified for THIS checkpoint — if the boot
|
|
|
# rejects it (the GLM C4 page-stride / interleave-multiple-of-4 gates), drop
|
