feat: Add comprehensive RDMA cluster setup guide, enforce eager mode in cluster benchmarks, and update documentation with cluster details.

This commit is contained in:
Donato Capitella
2026-02-02 19:34:33 +00:00
vanhempi 1ddcb9a202
commit 1f96c391fb
6 muutettua tiedostoa jossa 405 lisäystä ja 10 poistoa
+3 -1
Näytä tiedosto
@@ -158,7 +158,8 @@ def get_model_args(model):
if config.get("trust_remote"): cmd.append("--trust-remote-code")
if config.get("enforce_eager"): cmd.append("--enforce-eager")
# Force eager mode for cluster stability
cmd.append("--enforce-eager")
return cmd
@@ -266,6 +267,7 @@ if __name__ == "__main__":
log("Ray Cluster Detected. Starting Benchmarks (Dual Backend)...")
log("Note: Eager Mode (--enforce-eager) is ENABLED for cluster stability.")
for m in MODELS_TO_RUN:
run_cluster_throughput(m)