[ { "case": "10k-warm", "index": 0, "variant": "baseline", "exit": 0, "seconds": 37.28526037497795, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_albedo_11k.txt", "--n-prompt", "10180", "--n-gen", "32" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-kernels" }, "metrics": { "init_ms": "14139.98", "prompt_tokens": "10180", "prefill_ms": "21641.96", "prefill_tok_s": "470.38", "decode_tokens": "31", "decode_ms": "888.16", "decode_tok_s": "34.90", "decode_ms_per_tok": "28.65" } }, { "case": "10k-warm", "index": 1, "variant": "candidate", "exit": 0, "seconds": 26.902124457992613, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_albedo_11k.txt", "--n-prompt", "10180", "--n-gen", "32" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-kernels" }, "metrics": { "init_ms": "3039.06", "prompt_tokens": "10180", "prefill_ms": "22208.75", "prefill_tok_s": "458.38", "decode_tokens": "31", "decode_ms": "891.67", "decode_tok_s": "34.77", "decode_ms_per_tok": "28.76" } }, { "case": "10k", "index": 0, "variant": "baseline", "exit": 0, "seconds": 27.85658016600064, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_albedo_11k.txt", "--n-prompt", "10180", "--n-gen", "32" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-kernels" }, "metrics": { "init_ms": "3103.75", "prompt_tokens": "10180", "prefill_ms": "23415.08", "prefill_tok_s": "434.76", "decode_tokens": "31", "decode_ms": "908.29", "decode_tok_s": "34.13", "decode_ms_per_tok": "29.30" } }, { "case": "10k", "index": 1, "variant": "candidate", "exit": 0, "seconds": 29.545378999988316, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_albedo_11k.txt", "--n-prompt", "10180", "--n-gen", "32" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-kernels" }, "metrics": { "init_ms": "4106.98", "prompt_tokens": "10180", "prefill_ms": "24080.38", "prefill_tok_s": "422.75", "decode_tokens": "31", "decode_ms": "920.70", "decode_tok_s": "33.67", "decode_ms_per_tok": "29.70" } }, { "case": "10k", "index": 2, "variant": "candidate", "exit": 0, "seconds": 28.710599082987756, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_albedo_11k.txt", "--n-prompt", "10180", "--n-gen", "32" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-kernels" }, "metrics": { "init_ms": "3115.54", "prompt_tokens": "10180", "prefill_ms": "24248.45", "prefill_tok_s": "419.82", "decode_tokens": "31", "decode_ms": "915.71", "decode_tok_s": "33.85", "decode_ms_per_tok": "29.54" } }, { "case": "10k", "index": 3, "variant": "baseline", "exit": 0, "seconds": 32.19512254098663, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_albedo_11k.txt", "--n-prompt", "10180", "--n-gen", "32" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-kernels" }, "metrics": { "init_ms": "4189.01", "prompt_tokens": "10180", "prefill_ms": "26637.98", "prefill_tok_s": "382.16", "decode_tokens": "31", "decode_ms": "949.61", "decode_tok_s": "32.64", "decode_ms_per_tok": "30.63" } }, { "case": "10k", "index": 4, "variant": "baseline", "exit": 0, "seconds": 32.90031333299703, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_albedo_11k.txt", "--n-prompt", "10180", "--n-gen", "32" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-kernels" }, "metrics": { "init_ms": "2935.91", "prompt_tokens": "10180", "prefill_ms": "28519.16", "prefill_tok_s": "356.95", "decode_tokens": "31", "decode_ms": "996.64", "decode_tok_s": "31.10", "decode_ms_per_tok": "32.15" } }, { "case": "10k", "index": 5, "variant": "candidate", "exit": 0, "seconds": 35.647112042002846, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_albedo_11k.txt", "--n-prompt", "10180", "--n-gen", "32" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-kernels" }, "metrics": { "init_ms": "3740.62", "prompt_tokens": "10180", "prefill_ms": "30410.22", "prefill_tok_s": "334.76", "decode_tokens": "31", "decode_ms": "1024.55", "decode_tok_s": "30.26", "decode_ms_per_tok": "33.05" } }, { "case": "2k", "index": 0, "variant": "baseline", "exit": 0, "seconds": 14.231617666024249, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_2048tok_ops.txt", "--n-prompt", "1984", "--n-gen", "128" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-kernels" }, "metrics": { "init_ms": "3523.84", "prompt_tokens": "1984", "prefill_ms": "6219.43", "prefill_tok_s": "319.00", "decode_tokens": "127", "decode_ms": "3997.56", "decode_tok_s": "31.77", "decode_ms_per_tok": "31.48" } }, { "case": "2k", "index": 1, "variant": "candidate", "exit": 0, "seconds": 15.059506499994313, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_2048tok_ops.txt", "--n-prompt", "1984", "--n-gen", "128" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-kernels" }, "metrics": { "init_ms": "3630.76", "prompt_tokens": "1984", "prefill_ms": "6868.23", "prefill_tok_s": "288.87", "decode_tokens": "127", "decode_ms": "4056.08", "decode_tok_s": "31.31", "decode_ms_per_tok": "31.94" } }, { "case": "2k", "index": 2, "variant": "candidate", "exit": 0, "seconds": 14.592543375008972, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_2048tok_ops.txt", "--n-prompt", "1984", "--n-gen", "128" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/candidate-kernels" }, "metrics": { "init_ms": "3336.81", "prompt_tokens": "1984", "prefill_ms": "6534.59", "prefill_tok_s": "303.61", "decode_tokens": "127", "decode_ms": "4213.72", "decode_tok_s": "30.14", "decode_ms_per_tok": "33.18" } }, { "case": "2k", "index": 3, "variant": "baseline", "exit": 0, "seconds": 15.292481250013225, "argv": [ "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-cli", "--metal-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/k512-iq2_xs-metal.gguf", "--ple-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K256_reap_l2_sum/Swift-Qwen3.8-Flash-Next-GSQ-RCO-IQ3_S-K256_reap_l2_sum-00001-of-00002.gguf", "--mtp-gguf", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/models/K512_iq2_xs/mtp-q2_0.gguf", "--n-expert", "512", "--ctx", "32768", "--spec", "3", "--spec-min-p", "0.35", "--suffix-draft", "3", "--tokens-file", "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/data/m5_val_prompts/prompt_2048tok_ops.txt", "--n-prompt", "1984", "--n-gen", "128" ], "env": { "STRATA_METAL_ARENA_GB": "6.5", "STRATA_METAL_MLOCK_DENSE": "1", "STRATA_METAL_WIRE_ARENA": "1", "STRATA_METAL_EXPERT_PROFILE": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/vendor/strata/data/expert-profile.bin", "STRATA_METAL_MOCE_BONUS": "0.85", "STRATA_METAL_EXPERT_SPLIT": "1", "STRATA_METAL_SHEXP_OVERLAP": "1", "STRATA_METAL_SPLIT_TURN": "1", "STRATA_METAL_PRED_Q8": "1", "STRATA_METAL_ROUTER_BF16": "1", "STRATA_METAL_MOE_DN_TILE": "8,2,4", "STRATA_METAL_PREFETCH": "6", "STRATA_METAL_PREFETCH2": "2", "STRATA_METAL_IO_THREADS": "8", "STRATA_METAL_IO_URGENT": "2", "STRATA_ANTI_SLOP_PENALTY": "9.0", "STRATA_ANTI_SLOP_HONEST": "6.0", "STRATA_ANTI_SLOP_MD": "4.0", "STRATA_ANTI_SLOP_COLON": "3.0", "STRATA_METAL_PROMPT_CHUNK": "2048", "STRATA_METAL_PREFETCH_DRAFT": "0", "STRATA_METAL_PUBLISH_PREFETCH": "1", "STRATA_METAL_MTP_SLOP": "1", "STRATA_METAL_DRAFT_MOCE": "1", "STRATA_METAL_TRACE": "1", "STRATA_METAL_KERNELS": "/Users/dawn/proj/swift1.5-qwen3.8-next-flash-ps-scr-qat-persona/results/round39/model-ab/baseline-kernels" }, "metrics": { "init_ms": "3886.19", "prompt_tokens": "1984", "prefill_ms": "6764.25", "prefill_tok_s": "293.31", "decode_tokens": "127", "decode_ms": "4143.13", "decode_tok_s": "30.65", "decode_ms_per_tok": "32.62" } } ]