diff --git a/scripts/cache_aware_proxy.py b/scripts/cache_aware_proxy.py index 1dead20..58c00dc 100644 --- a/scripts/cache_aware_proxy.py +++ b/scripts/cache_aware_proxy.py @@ -613,16 +613,6 @@ async def _handle_combined(api, req_data, token_ids, input_length, session_id, h return await _handle_local_request( api, req_data, headers, token_ids, input_length, chosen, estimated_new, breakdown) - if push_new < SETTINGS.heavy_threshold: - breakdown["push_downgraded"] = "below_heavy_threshold" - return await _handle_local_request( - api, req_data, headers, token_ids, input_length, - chosen, estimated_new, breakdown) - if SETTINGS.cache_gate_ratio > 0 and cache_ratio < SETTINGS.cache_gate_ratio: - breakdown["push_downgraded"] = "cache_gate" - return await _handle_local_request( - api, req_data, headers, token_ids, input_length, - chosen, estimated_new, breakdown) offload_mode = getattr(global_args, 'offload_mode', 'cached_prefill') breakdown["c_inst"] = c_inst.url