{ "completion": { "conditions": 9, "estimated_values": 0, "failed": 0, "oom_events": 0, "successful": 9 }, "environment": { "cuda_driver": "610.57.04", "cuda_runtime": "13.0", "gpu": "NVIDIA GeForce RTX 3050 Laptop GPU", "gpu_total_bytes": 3950575616, "platform": "Linux-7.1.8-1-MANJARO-x86_64-with-glibc2.44", "python": "3.12.6", "torch": "2.13.0+cu130", "transformers": "5.15.1" }, "experiment": "planner-cache-matched-vram-comparison-v1", "method": { "attention_working_memory": "present in every condition and distinct from retained KV cache", "baseline": "CUDA allocation after loaded stack and empty_cache", "combined": "retained KV and P-cache TTL path active together", "kv_only": "retained KV active while P-cache and TTL injection are disabled", "model_load": "one frozen model, TTL, and router reused for every condition", "p_cache_only": "retained KV disabled while P-cache and TTL are active", "peak": "torch.cuda reset_peak_memory_stats and synchronized measurement", "warmup": "all measured mechanisms exercised once before baselines" }, "model": { "config_sha256": "6ea552aa42b7437f019ccdd30b7c9b83a32dccb5170ce31b9ddbe94d00f4671c", "identifier": "pythia-1.4b", "router_filename": "canonical-p-v1.router", "router_sha256": "29e0728c12f8806c48998579aedcfa389fa398f909098e162710eb2a5709834e", "ttl_filename": "pythia-1.4b-final-layer.ttl", "ttl_sha256": "72ef68d07ee27c37b90432d34d4be5c2c280ae1bcb08236e37a0e458c054d8d7" }, "results": [ { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "p_cache_only", "failure": null, "fallback": null, "final_sequence_tokens": 72, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 7471616, "incremental_peak_reserved_bytes": 4194304, "p_cache_canonical_bytes": 134464, "p_cache_enabled": true, "p_cache_slots": 64, "peak_allocated_bytes": 2856644608, "peak_reserved_bytes": 2910846976, "precision": "float16 base and float32 TTL", "prompt_tokens": 64, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 0, "retained_kv_enabled": false, "runtime_seconds": 0.2554637499997625 }, { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "kv_only", "failure": null, "fallback": null, "final_sequence_tokens": 72, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 19284992, "incremental_peak_reserved_bytes": 16777216, "p_cache_canonical_bytes": 0, "p_cache_enabled": false, "p_cache_slots": 0, "peak_allocated_bytes": 2868457984, "peak_reserved_bytes": 2923429888, "precision": "float16 base and float32 TTL", "prompt_tokens": 64, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 13959168, "retained_kv_enabled": true, "runtime_seconds": 0.17538804200012237 }, { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "p_cache_plus_kv", "failure": null, "fallback": null, "final_sequence_tokens": 72, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 19319808, "incremental_peak_reserved_bytes": 16777216, "p_cache_canonical_bytes": 134464, "p_cache_enabled": true, "p_cache_slots": 64, "peak_allocated_bytes": 2868492800, "peak_reserved_bytes": 2923429888, "precision": "float16 base and float32 TTL", "prompt_tokens": 64, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 13959168, "retained_kv_enabled": true, "runtime_seconds": 0.20454967800469603 }, { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "p_cache_only", "failure": null, "fallback": null, "final_sequence_tokens": 264, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 28483584, "incremental_peak_reserved_bytes": 35651584, "p_cache_canonical_bytes": 537856, "p_cache_enabled": true, "p_cache_slots": 256, "peak_allocated_bytes": 2877656576, "peak_reserved_bytes": 2942304256, "precision": "float16 base and float32 TTL", "prompt_tokens": 256, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 0, "retained_kv_enabled": false, "runtime_seconds": 0.7414951529935934 }, { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "kv_only", "failure": null, "fallback": null, "final_sequence_tokens": 264, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 81187328, "incremental_peak_reserved_bytes": 83886080, "p_cache_canonical_bytes": 0, "p_cache_enabled": false, "p_cache_slots": 0, "peak_allocated_bytes": 2930360320, "peak_reserved_bytes": 2990538752, "precision": "float16 base and float32 TTL", "prompt_tokens": 256, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 51707904, "retained_kv_enabled": true, "runtime_seconds": 0.19367339000746142 }, { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "p_cache_plus_kv", "failure": null, "fallback": null, "final_sequence_tokens": 264, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 81323520, "incremental_peak_reserved_bytes": 83886080, "p_cache_canonical_bytes": 537856, "p_cache_enabled": true, "p_cache_slots": 256, "peak_allocated_bytes": 2930496512, "peak_reserved_bytes": 2990538752, "precision": "float16 base and float32 TTL", "prompt_tokens": 256, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 51707904, "retained_kv_enabled": true, "runtime_seconds": 0.41562580699974205 }, { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "p_cache_only", "failure": null, "fallback": null, "final_sequence_tokens": 1032, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 108517888, "incremental_peak_reserved_bytes": 174063616, "p_cache_canonical_bytes": 2151424, "p_cache_enabled": true, "p_cache_slots": 1024, "peak_allocated_bytes": 2957690880, "peak_reserved_bytes": 3080716288, "precision": "float16 base and float32 TTL", "prompt_tokens": 1024, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 0, "retained_kv_enabled": false, "runtime_seconds": 2.710468404009589 }, { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "kv_only", "failure": null, "fallback": null, "final_sequence_tokens": 1032, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 308559872, "incremental_peak_reserved_bytes": 339738624, "p_cache_canonical_bytes": 0, "p_cache_enabled": false, "p_cache_slots": 0, "peak_allocated_bytes": 3157732864, "peak_reserved_bytes": 3246391296, "precision": "float16 base and float32 TTL", "prompt_tokens": 1024, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 202702848, "retained_kv_enabled": true, "runtime_seconds": 0.37531103400397114 }, { "baseline_allocated_bytes": 2849172992, "baseline_reserved_bytes": 2906652672, "batch_size": 1, "condition": "p_cache_plus_kv", "failure": null, "fallback": null, "final_sequence_tokens": 1032, "generated_tokens": 8, "generation": "greedy argmax", "incremental_peak_allocated_bytes": 309102080, "incremental_peak_reserved_bytes": 358612992, "p_cache_canonical_bytes": 2151424, "p_cache_enabled": true, "p_cache_slots": 1024, "peak_allocated_bytes": 3158275072, "peak_reserved_bytes": 3265265664, "precision": "float16 base and float32 TTL", "prompt_tokens": 1024, "requested_generated_tokens": 8, "retained_kv_cache_bytes": 202702848, "retained_kv_enabled": true, "runtime_seconds": 1.2812230650015408 } ], "shared_configuration": { "batch_size": 1, "generated_tokens": 8, "generation": "greedy argmax", "precision": "float16 base and float32 TTL", "seed": 317, "workload_prompt_and_slot_sizes": [ 64, 256, 1024 ] } }