diff --git a/runs/frontier-multicase-sufficiency-v0/best_effort/fixed_cohort_rank.py b/runs/frontier-multicase-sufficiency-v0/best_effort/fixed_cohort_rank.py index 78d4f58..ca29fd9 100644 --- a/runs/frontier-multicase-sufficiency-v0/best_effort/fixed_cohort_rank.py +++ b/runs/frontier-multicase-sufficiency-v0/best_effort/fixed_cohort_rank.py @@ -631,6 +631,7 @@ def run_frontier(args: argparse.Namespace) -> Path: "quantization": "block_fp8_w8a8_dynamic_with_bf16_output_accumulation", "execution_profiles": "community_vllm_0.10.2_serving_entrypoints", "moe_ep_prefill": "global_routing_then_slowest_local_ep_lane", + "moe_ep_critical_lane_cache": "exact_(total_routed_tokens,layer_id)_memoization", "kv_blocks": "measured_community_vllm_and_fixed_per_topology", "cpu_overhead_modeling": "disabled_no_native_community_vllm_records", "end_to_end_action_specific_calibration": False, diff --git a/runs/frontier-multicase-sufficiency-v0/best_effort/frontier_moe_ep_prefill_exact_cache.patch b/runs/frontier-multicase-sufficiency-v0/best_effort/frontier_moe_ep_prefill_exact_cache.patch new file mode 100644 index 0000000..0bb9203 --- /dev/null +++ b/runs/frontier-multicase-sufficiency-v0/best_effort/frontier_moe_ep_prefill_exact_cache.patch @@ -0,0 +1,17 @@ +diff --git a/frontier/execution_time_predictor/sklearn_moe_execution_time_predictor.py b/frontier/execution_time_predictor/sklearn_moe_execution_time_predictor.py +--- a/frontier/execution_time_predictor/sklearn_moe_execution_time_predictor.py ++++ b/frontier/execution_time_predictor/sklearn_moe_execution_time_predictor.py +@@ -1,4 +1,5 @@ + from typing import Any, Dict, List, Optional, TYPE_CHECKING, Union ++from functools import lru_cache + import os + + import numpy as np +@@ -384,6 +385,7 @@ + allocation_ratios=allocation_ratios, + ) + ++ @lru_cache(maxsize=None) + def _get_critical_prefill_ep_lane_tokens( + self, + total_routed_tokens: int,