{ "environment": { "platform": "macOS-27.0.1-arm64-arm-64bit", "machine": "arm64", "metal": { "device_name": "Apple M5 Pro", "max_recommended_working_set_size": 55662788608, "memory_size": 68719476736, "architecture": "applegpu_g17s", "max_buffer_length": 41747087360, "resource_limit": 499000 }, "versions": { "mlx": "0.32.4", "mlx-metal": "0.32.4", "numpy": "2.5.4", "safetensors": "0.8.0", "transformers": "4.57.6", "torch": "2.15.0" }, "precision_environment": { "MLX_ENABLE_TF32": "0", "MLX_CONV_WINOGRAD": "0" } }, "warmup": 2, "repeats": 7, "scope": "Synthetic operator microbenchmarks; excludes loading/quantization. Not image latency.", "trials": [ { "operator": "rms_adaln", "variant": "native_rounding", "shape": [ 256, 5376 ], "median_ms": 1.173374941572547, "min_ms": 0.616749981418252, "max_ms": 1.2301669921725988, "samples_ms": [ 0.616749981418252, 1.2266251724213362, 1.0637501254677773, 1.173374941572547, 1.2301669921725988, 1.195583026856184, 1.1052920017391443 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "rms_adaln", "variant": "metal_tg128", "shape": [ 256, 5376 ], "median_ms": 0.5940420087426901, "min_ms": 0.5400839727371931, "max_ms": 0.7085409015417099, "samples_ms": [ 0.7085409015417099, 0.5697500891983509, 0.5824591498821974, 0.5400839727371931, 0.6797090172767639, 0.5940420087426901, 0.609041890129447 ], "max_abs": 0.015625, "relative_rmse": 1.7477590517955832e-05, "equal_fraction": 0.9999935030937195 }, { "operator": "rms_adaln", "variant": "metal_tg256", "shape": [ 256, 5376 ], "median_ms": 0.5604161415249109, "min_ms": 0.2424169797450304, "max_ms": 0.6824578158557415, "samples_ms": [ 0.6682500243186951, 0.5432919133454561, 0.6824578158557415, 0.6537078879773617, 0.5389170255511999, 0.5604161415249109, 0.2424169797450304 ], "max_abs": 0.015625, "relative_rmse": 2.209606464020908e-05, "equal_fraction": 0.9999912977218628 }, { "operator": "rms_adaln", "variant": "metal_tg512", "shape": [ 256, 5376 ], "median_ms": 0.8023330010473728, "min_ms": 0.19370880909264088, "max_ms": 0.8323339279741049, "samples_ms": [ 0.8323339279741049, 0.8083749562501907, 0.8090410847216845, 0.7428331300616264, 0.8023330010473728, 0.19370880909264088, 0.7230001501739025 ], "max_abs": 0.015625, "relative_rmse": 1.8376344087300822e-05, "equal_fraction": 0.9999912977218628 }, { "operator": "qk_norm_rope", "variant": "native", "shape": [ 256, 56, 128 ], "median_ms": 1.1400829534977674, "min_ms": 0.6993331480771303, "max_ms": 1.366166863590479, "samples_ms": [ 0.7345420308411121, 0.7162499241530895, 0.6993331480771303, 1.2012079823762178, 1.366166863590479, 1.1400829534977674, 1.2222910299897194 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "qk_norm_rope", "variant": "metal", "shape": [ 256, 56, 128 ], "median_ms": 0.26829191483557224, "min_ms": 0.24679210036993027, "max_ms": 0.9639160707592964, "samples_ms": [ 0.9639160707592964, 0.848833005875349, 0.8924168068915606, 0.26829191483557224, 0.24679210036993027, 0.264165922999382, 0.2524999435991049 ], "max_abs": 0.00390625, "relative_rmse": 3.6376052321429597e-06, "equal_fraction": 0.9999983906745911 }, { "operator": "gemm", "variant": "bf16", "shape": [ 256, 5376, 21504 ], "median_ms": 2.5721671991050243, "min_ms": 2.5016670115292072, "max_ms": 2.6360841002315283, "samples_ms": [ 2.5721671991050243, 2.580333035439253, 2.587541937828064, 2.5619592051953077, 2.550124889239669, 2.6360841002315283, 2.5016670115292072 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "gemm", "variant": "q8_g32", "shape": [ 256, 5376, 21504 ], "median_ms": 3.0226248782128096, "min_ms": 3.0050419736653566, "max_ms": 3.1408751383423805, "samples_ms": [ 3.018749877810478, 3.040374955162406, 3.0050419736653566, 3.1321251299232244, 3.1408751383423805, 3.0226248782128096, 3.0074999667704105 ], "max_abs": 0.0625, "relative_rmse": 0.006850533653050661, "equal_fraction": 0.24900999665260315 }, { "operator": "gemm", "variant": "q8_g64", "shape": [ 256, 5376, 21504 ], "median_ms": 2.9889577999711037, "min_ms": 2.945707878097892, "max_ms": 3.2797919120639563, "samples_ms": [ 3.110166173428297, 3.0175000429153442, 3.2797919120639563, 2.9889577999711037, 2.970875008031726, 2.945707878097892, 2.9832920990884304 ], "max_abs": 0.0625, "relative_rmse": 0.007352763321250677, "equal_fraction": 0.23354558646678925 }, { "operator": "gemm", "variant": "q8_g128", "shape": [ 256, 5376, 21504 ], "median_ms": 2.979417098686099, "min_ms": 2.963416976854205, "max_ms": 3.222458064556122, "samples_ms": [ 2.9804580844938755, 3.222458064556122, 3.1075000297278166, 2.969249850139022, 2.963416976854205, 2.979417098686099, 2.9705839697271585 ], "max_abs": 0.0625, "relative_rmse": 0.007834218442440033, "equal_fraction": 0.22005045413970947 }, { "operator": "gemm", "variant": "q4_g32", "shape": [ 256, 5376, 21504 ], "median_ms": 2.7746250852942467, "min_ms": 2.7560831513255835, "max_ms": 3.058916889131069, "samples_ms": [ 3.058916889131069, 2.7560831513255835, 2.7758749201893806, 2.8548329137265682, 2.7711251750588417, 2.7608750388026237, 2.7746250852942467 ], "max_abs": 0.64453125, "relative_rmse": 0.08106927573680878, "equal_fraction": 0.0220609400421381 }, { "operator": "gemm", "variant": "q4_g64", "shape": [ 256, 5376, 21504 ], "median_ms": 2.7238749898970127, "min_ms": 2.707334002479911, "max_ms": 2.966000000014901, "samples_ms": [ 2.966000000014901, 2.7539171278476715, 2.7230000123381615, 2.7238749898970127, 2.711624838411808, 2.7322079986333847, 2.707334002479911 ], "max_abs": 0.6953125, "relative_rmse": 0.0909692719578743, "equal_fraction": 0.01975395530462265 }, { "operator": "gemm", "variant": "q4_g128", "shape": [ 256, 5376, 21504 ], "median_ms": 2.727207960560918, "min_ms": 2.6830830611288548, "max_ms": 2.914041979238391, "samples_ms": [ 2.9036658816039562, 2.914041979238391, 2.7150840032845736, 2.8310411144047976, 2.727207960560918, 2.6830830611288548, 2.6853750459849834 ], "max_abs": 0.7509765625, "relative_rmse": 0.09998571127653122, "equal_fraction": 0.017951058223843575 }, { "operator": "gemm", "variant": "bf16", "shape": [ 256, 5376, 28672 ], "median_ms": 3.347999881953001, "min_ms": 3.28362500295043, "max_ms": 3.5925419069826603, "samples_ms": [ 3.347999881953001, 3.2983338460326195, 3.5925419069826603, 3.4004999324679375, 3.321249969303608, 3.3945830073207617, 3.28362500295043 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "gemm", "variant": "q8_g32", "shape": [ 256, 5376, 28672 ], "median_ms": 3.924708114936948, "min_ms": 3.8868330884724855, "max_ms": 3.9580839220434427, "samples_ms": [ 3.924708114936948, 3.9580839220434427, 3.9263751823455095, 3.929541911929846, 3.8885409012436867, 3.8868330884724855, 3.892374923452735 ], "max_abs": 0.0625, "relative_rmse": 0.0068595209158957005, "equal_fraction": 0.24881459772586823 }, { "operator": "gemm", "variant": "q8_g64", "shape": [ 256, 5376, 28672 ], "median_ms": 3.9282499346882105, "min_ms": 3.88133293017745, "max_ms": 4.043041029945016, "samples_ms": [ 3.9579591248184443, 3.8992909248918295, 3.886499907821417, 4.043041029945016, 3.963541006669402, 3.88133293017745, 3.9282499346882105 ], "max_abs": 0.0625, "relative_rmse": 0.007344856392592192, "equal_fraction": 0.23325484991073608 }, { "operator": "gemm", "variant": "q8_g128", "shape": [ 256, 5376, 28672 ], "median_ms": 3.890999825671315, "min_ms": 3.86029202491045, "max_ms": 4.0629159193485975, "samples_ms": [ 4.019708139821887, 3.86029202491045, 3.8872910663485527, 3.864959115162492, 4.0629159193485975, 3.9462910499423742, 3.890999825671315 ], "max_abs": 0.0625, "relative_rmse": 0.007839743979275227, "equal_fraction": 0.21977084875106812 }, { "operator": "gemm", "variant": "q4_g32", "shape": [ 256, 5376, 28672 ], "median_ms": 3.6355829797685146, "min_ms": 3.614082932472229, "max_ms": 3.8034170866012573, "samples_ms": [ 3.6440829280763865, 3.622000105679035, 3.663749899715185, 3.6355829797685146, 3.6264171358197927, 3.8034170866012573, 3.614082932472229 ], "max_abs": 0.63214111328125, "relative_rmse": 0.08107927441596985, "equal_fraction": 0.02212129347026348 }, { "operator": "gemm", "variant": "q4_g64", "shape": [ 256, 5376, 28672 ], "median_ms": 3.5808749962598085, "min_ms": 3.555125091224909, "max_ms": 3.729666117578745, "samples_ms": [ 3.5808749962598085, 3.5678748972713947, 3.729666117578745, 3.6466249730437994, 3.5678751301020384, 3.6204170901328325, 3.555125091224909 ], "max_abs": 0.7109375, "relative_rmse": 0.09099964797496796, "equal_fraction": 0.01962498389184475 }, { "operator": "gemm", "variant": "q4_g128", "shape": [ 256, 5376, 28672 ], "median_ms": 3.5667498596012592, "min_ms": 3.5494170151650906, "max_ms": 3.6764999385923147, "samples_ms": [ 3.6764999385923147, 3.553125075995922, 3.5667498596012592, 3.5774579737335443, 3.5494170151650906, 3.554082941263914, 3.568042069673538 ], "max_abs": 0.84375, "relative_rmse": 0.10004469007253647, "equal_fraction": 0.017870495095849037 }, { "operator": "gemm", "variant": "bf16", "shape": [ 256, 14336, 5376 ], "median_ms": 2.098832977935672, "min_ms": 2.0805420354008675, "max_ms": 2.1304998081177473, "samples_ms": [ 2.113000024110079, 2.098832977935672, 2.1304998081177473, 2.094374969601631, 2.0852498710155487, 2.1142091136425734, 2.0805420354008675 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "gemm", "variant": "q8_g32", "shape": [ 256, 14336, 5376 ], "median_ms": 2.3393749725073576, "min_ms": 2.302875043824315, "max_ms": 2.5676661171019077, "samples_ms": [ 2.3640000727027655, 2.5676661171019077, 2.556499792262912, 2.3393749725073576, 2.338541904464364, 2.302875043824315, 2.3251669481396675 ], "max_abs": 0.0859375, "relative_rmse": 0.006851653102785349, "equal_fraction": 0.2485344409942627 }, { "operator": "gemm", "variant": "q8_g64", "shape": [ 256, 14336, 5376 ], "median_ms": 2.398208947852254, "min_ms": 2.242250135168433, "max_ms": 2.6454171165823936, "samples_ms": [ 2.398208947852254, 2.2548330016434193, 2.5238750968128443, 2.6454171165823936, 2.398416865617037, 2.37491587176919, 2.242250135168433 ], "max_abs": 0.09375, "relative_rmse": 0.007338221650570631, "equal_fraction": 0.2334180623292923 }, { "operator": "gemm", "variant": "q8_g128", "shape": [ 256, 14336, 5376 ], "median_ms": 2.2256250958889723, "min_ms": 2.209833823144436, "max_ms": 2.2738338448107243, "samples_ms": [ 2.2117909975349903, 2.214916981756687, 2.209833823144436, 2.263291971758008, 2.2330000065267086, 2.2256250958889723, 2.2738338448107243 ], "max_abs": 0.09375, "relative_rmse": 0.007827789522707462, "equal_fraction": 0.2200208455324173 }, { "operator": "gemm", "variant": "q4_g32", "shape": [ 256, 14336, 5376 ], "median_ms": 2.159459050744772, "min_ms": 2.059374935925007, "max_ms": 2.193290973082185, "samples_ms": [ 2.059374935925007, 2.18175002373755, 2.159459050744772, 2.075666096061468, 2.193290973082185, 2.122832927852869, 2.159666968509555 ], "max_abs": 0.9296875, "relative_rmse": 0.08106718212366104, "equal_fraction": 0.02191670797765255 }, { "operator": "gemm", "variant": "q4_g64", "shape": [ 256, 14336, 5376 ], "median_ms": 2.067500026896596, "min_ms": 1.9949160050600767, "max_ms": 2.128707943484187, "samples_ms": [ 2.067500026896596, 2.0210829097777605, 2.096999902278185, 2.128707943484187, 1.9949160050600767, 2.0117908716201782, 2.0698329899460077 ], "max_abs": 1.0390625, "relative_rmse": 0.09107401221990585, "equal_fraction": 0.0195334292948246 }, { "operator": "gemm", "variant": "q4_g128", "shape": [ 256, 14336, 5376 ], "median_ms": 2.079749945551157, "min_ms": 2.0619581919163465, "max_ms": 2.380209043622017, "samples_ms": [ 2.0619581919163465, 2.0739170722663403, 2.1086670458316803, 2.079749945551157, 2.380209043622017, 2.083666855469346, 2.062832936644554 ], "max_abs": 1.171875, "relative_rmse": 0.10009276866912842, "equal_fraction": 0.01786004938185215 }, { "operator": "sdpa", "variant": "query_chunk_0", "shape": [ 1, 256, 56, 128 ], "median_ms": 0.32275007106363773, "min_ms": 0.31208316795527935, "max_ms": 0.3370409831404686, "samples_ms": [ 0.3233749885112047, 0.32275007106363773, 0.31208316795527935, 0.31349994242191315, 0.33125001937150955, 0.3370409831404686, 0.31766598112881184 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "sdpa", "variant": "query_chunk_128", "shape": [ 1, 256, 56, 128 ], "median_ms": 0.6250408478081226, "min_ms": 0.5880000535398722, "max_ms": 0.684875063598156, "samples_ms": [ 0.684875063598156, 0.6232080049812794, 0.6250408478081226, 0.6210829596966505, 0.631541945040226, 0.632166862487793, 0.5880000535398722 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "sdpa", "variant": "query_chunk_512", "shape": [ 1, 256, 56, 128 ], "median_ms": 0.28816587291657925, "min_ms": 0.25708298198878765, "max_ms": 0.2957081887871027, "samples_ms": [ 0.2957081887871027, 0.29191700741648674, 0.28900010511279106, 0.27449987828731537, 0.28816587291657925, 0.2626250497996807, 0.25708298198878765 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "sdpa", "variant": "query_chunk_1024", "shape": [ 1, 256, 56, 128 ], "median_ms": 0.2906669396907091, "min_ms": 0.2794580068439245, "max_ms": 0.3147500101476908, "samples_ms": [ 0.27962494641542435, 0.2935829106718302, 0.29037497006356716, 0.3147500101476908, 0.2794580068439245, 0.2906669396907091, 0.2928751055151224 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "rms_adaln", "variant": "native_rounding", "shape": [ 4096, 5376 ], "median_ms": 3.5581670235842466, "min_ms": 3.5174579825252295, "max_ms": 3.779958002269268, "samples_ms": [ 3.5195830278098583, 3.706582821905613, 3.779958002269268, 3.5999580286443233, 3.5581670235842466, 3.530999878421426, 3.5174579825252295 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "rms_adaln", "variant": "metal_tg128", "shape": [ 4096, 5376 ], "median_ms": 0.5828330758959055, "min_ms": 0.5625830963253975, "max_ms": 0.7374170236289501, "samples_ms": [ 0.5748749244958162, 0.6655419711023569, 0.5828330758959055, 0.5625830963253975, 0.7374170236289501, 0.5845420528203249, 0.5679160822182894 ], "max_abs": 0.03125, "relative_rmse": 1.081336540664779e-05, "equal_fraction": 0.9999977350234985 }, { "operator": "rms_adaln", "variant": "metal_tg256", "shape": [ 4096, 5376 ], "median_ms": 0.542541965842247, "min_ms": 0.5144169554114342, "max_ms": 0.5596249829977751, "samples_ms": [ 0.547375064343214, 0.5328329280018806, 0.5336250178515911, 0.5144169554114342, 0.5596249829977751, 0.542541965842247, 0.5430420860648155 ], "max_abs": 0.015625, "relative_rmse": 9.978849448089022e-06, "equal_fraction": 0.9999976754188538 }, { "operator": "rms_adaln", "variant": "metal_tg512", "shape": [ 4096, 5376 ], "median_ms": 0.5379160866141319, "min_ms": 0.5112909711897373, "max_ms": 0.5407920107245445, "samples_ms": [ 0.5379160866141319, 0.5390408914536238, 0.5112909711897373, 0.5176248960196972, 0.5320410709828138, 0.5397088825702667, 0.5407920107245445 ], "max_abs": 0.03125, "relative_rmse": 1.3310983376868535e-05, "equal_fraction": 0.9999973177909851 }, { "operator": "qk_norm_rope", "variant": "native", "shape": [ 4096, 56, 128 ], "median_ms": 10.960625018924475, "min_ms": 10.198707925155759, "max_ms": 13.119417009875178, "samples_ms": [ 13.119417009875178, 12.153874849900603, 11.330457869917154, 10.960625018924475, 10.477333795279264, 10.198707925155759, 10.489040985703468 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "qk_norm_rope", "variant": "metal", "shape": [ 4096, 56, 128 ], "median_ms": 2.057416830211878, "min_ms": 2.032166812568903, "max_ms": 2.1125830244272947, "samples_ms": [ 2.1125830244272947, 2.032166812568903, 2.0543329883366823, 2.108125016093254, 2.0634999964386225, 2.057416830211878, 2.04420811496675 ], "max_abs": 0.015625, "relative_rmse": 9.562711966282222e-06, "equal_fraction": 0.9999966621398926 }, { "operator": "gemm", "variant": "bf16", "shape": [ 4096, 5376, 21504 ], "median_ms": 37.58908296003938, "min_ms": 37.561249919235706, "max_ms": 37.69441717304289, "samples_ms": [ 37.66870801337063, 37.616125075146556, 37.69441717304289, 37.58908296003938, 37.573833018541336, 37.58049989119172, 37.561249919235706 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "gemm", "variant": "q8_g32", "shape": [ 4096, 5376, 21504 ], "median_ms": 43.576583033427596, "min_ms": 43.46295795403421, "max_ms": 43.9285000320524, "samples_ms": [ 43.9285000320524, 43.55879197828472, 43.46295795403421, 43.5891249217093, 43.576583033427596, 43.54733298532665, 43.7540418934077 ], "max_abs": 0.0625, "relative_rmse": 0.006848405115306377, "equal_fraction": 0.24890799820423126 }, { "operator": "gemm", "variant": "q8_g64", "shape": [ 4096, 5376, 21504 ], "median_ms": 43.335665948688984, "min_ms": 42.99841704778373, "max_ms": 43.70733303949237, "samples_ms": [ 43.32091589458287, 42.99841704778373, 43.70733303949237, 43.48420910537243, 43.335665948688984, 43.42833301052451, 43.065707897767425 ], "max_abs": 0.0625, "relative_rmse": 0.007345186080783606, "equal_fraction": 0.2333000749349594 }, { "operator": "gemm", "variant": "q8_g128", "shape": [ 4096, 5376, 21504 ], "median_ms": 43.26391592621803, "min_ms": 42.786624981090426, "max_ms": 43.67449996061623, "samples_ms": [ 43.431750033050776, 43.67449996061623, 43.26391592621803, 42.962417006492615, 42.786624981090426, 43.42845897190273, 43.2283750269562 ], "max_abs": 0.0703125, "relative_rmse": 0.00781948957592249, "equal_fraction": 0.22026407718658447 }, { "operator": "gemm", "variant": "q4_g32", "shape": [ 4096, 5376, 21504 ], "median_ms": 41.20029206387699, "min_ms": 41.03312501683831, "max_ms": 41.38141707517207, "samples_ms": [ 41.1425840575248, 41.38141707517207, 41.20029206387699, 41.150250006467104, 41.20558290742338, 41.33666702546179, 41.03312501683831 ], "max_abs": 0.71875, "relative_rmse": 0.0810740664601326, "equal_fraction": 0.022041741758584976 }, { "operator": "gemm", "variant": "q4_g64", "shape": [ 4096, 5376, 21504 ], "median_ms": 40.671000024303794, "min_ms": 40.518667083233595, "max_ms": 40.88425007648766, "samples_ms": [ 40.66379205323756, 40.611709002405405, 40.518667083233595, 40.88425007648766, 40.671000024303794, 40.70158419199288, 40.81641719676554 ], "max_abs": 0.763671875, "relative_rmse": 0.09098212420940399, "equal_fraction": 0.019682418555021286 }, { "operator": "gemm", "variant": "q4_g128", "shape": [ 4096, 5376, 21504 ], "median_ms": 40.219750022515655, "min_ms": 40.07566696964204, "max_ms": 40.326499845832586, "samples_ms": [ 40.313333040103316, 40.326499845832586, 40.219750022515655, 40.076584089547396, 40.18954187631607, 40.07566696964204, 40.235500084236264 ], "max_abs": 0.861328125, "relative_rmse": 0.10006927698850632, "equal_fraction": 0.01790381595492363 }, { "operator": "gemm", "variant": "bf16", "shape": [ 4096, 5376, 28672 ], "median_ms": 50.183625193312764, "min_ms": 50.01025018282235, "max_ms": 50.473124952986836, "samples_ms": [ 50.073042046278715, 50.473124952986836, 50.01025018282235, 50.22287485189736, 50.05783401429653, 50.183625193312764, 50.22233398631215 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "gemm", "variant": "q8_g32", "shape": [ 4096, 5376, 28672 ], "median_ms": 58.16854094155133, "min_ms": 57.83437518402934, "max_ms": 58.548124972730875, "samples_ms": [ 58.37570782750845, 58.548124972730875, 58.050625026226044, 58.243790874257684, 58.11225017532706, 58.16854094155133, 57.83437518402934 ], "max_abs": 0.0625, "relative_rmse": 0.0068477122113108635, "equal_fraction": 0.2489926517009735 }, { "operator": "gemm", "variant": "q8_g64", "shape": [ 4096, 5376, 28672 ], "median_ms": 57.96945793554187, "min_ms": 57.74970795027912, "max_ms": 58.27745795249939, "samples_ms": [ 58.05641692131758, 57.74970795027912, 57.96945793554187, 57.95050016604364, 58.27745795249939, 57.87858390249312, 57.978666853159666 ], "max_abs": 0.0625, "relative_rmse": 0.007344013080000877, "equal_fraction": 0.23339642584323883 }, { "operator": "gemm", "variant": "q8_g128", "shape": [ 4096, 5376, 28672 ], "median_ms": 58.31704195588827, "min_ms": 57.85416602157056, "max_ms": 58.81566694006324, "samples_ms": [ 57.94695811346173, 57.85416602157056, 58.45699994824827, 58.159250067546964, 58.31704195588827, 58.81566694006324, 58.56541683897376 ], "max_abs": 0.06640625, "relative_rmse": 0.00781780295073986, "equal_fraction": 0.2203386276960373 }, { "operator": "gemm", "variant": "q4_g32", "shape": [ 4096, 5376, 28672 ], "median_ms": 55.75945810414851, "min_ms": 54.988875053822994, "max_ms": 56.057958863675594, "samples_ms": [ 54.988875053822994, 55.60045805759728, 55.75945810414851, 55.441749980673194, 56.057958863675594, 55.944374995306134, 55.823208997026086 ], "max_abs": 0.6640625, "relative_rmse": 0.08107572048902512, "equal_fraction": 0.022053532302379608 }, { "operator": "gemm", "variant": "q4_g64", "shape": [ 4096, 5376, 28672 ], "median_ms": 55.38108292967081, "min_ms": 54.57354104146361, "max_ms": 55.79287512227893, "samples_ms": [ 54.57354104146361, 55.38108292967081, 55.60295912437141, 55.10041699744761, 55.79287512227893, 55.68016692996025, 55.32279098406434 ], "max_abs": 0.763916015625, "relative_rmse": 0.09099233150482178, "equal_fraction": 0.019668912515044212 }, { "operator": "gemm", "variant": "q4_g128", "shape": [ 4096, 5376, 28672 ], "median_ms": 55.30212516896427, "min_ms": 54.67195808887482, "max_ms": 55.79587514512241, "samples_ms": [ 54.813416907563806, 54.67195808887482, 55.29566598124802, 55.30212516896427, 55.365709122270346, 55.59012503363192, 55.79587514512241 ], "max_abs": 0.853515625, "relative_rmse": 0.10007014870643616, "equal_fraction": 0.017912209033966064 }, { "operator": "gemm", "variant": "bf16", "shape": [ 4096, 14336, 5376 ], "median_ms": 29.900042107328773, "min_ms": 28.89745798893273, "max_ms": 30.47887491993606, "samples_ms": [ 30.47887491993606, 29.908499913290143, 29.61533283814788, 28.89745798893273, 29.382749926298857, 29.900042107328773, 30.169625068083405 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "gemm", "variant": "q8_g32", "shape": [ 4096, 14336, 5376 ], "median_ms": 32.60995796881616, "min_ms": 32.3443750385195, "max_ms": 33.24191691353917, "samples_ms": [ 32.51500008627772, 32.3443750385195, 32.59654110297561, 32.8078749589622, 32.94933307915926, 32.60995796881616, 33.24191691353917 ], "max_abs": 0.09375, "relative_rmse": 0.006849921308457851, "equal_fraction": 0.24884523451328278 }, { "operator": "gemm", "variant": "q8_g64", "shape": [ 4096, 14336, 5376 ], "median_ms": 32.50916698016226, "min_ms": 31.81283315643668, "max_ms": 33.11962494626641, "samples_ms": [ 32.13399997912347, 31.956125050783157, 31.81283315643668, 32.66279213130474, 32.50916698016226, 33.11962494626641, 32.73437498137355 ], "max_abs": 0.09375, "relative_rmse": 0.0073441751301288605, "equal_fraction": 0.23339390754699707 }, { "operator": "gemm", "variant": "q8_g128", "shape": [ 4096, 14336, 5376 ], "median_ms": 32.53870899789035, "min_ms": 31.987624941393733, "max_ms": 32.83950011245906, "samples_ms": [ 32.462208066135645, 32.62395807541907, 32.83950011245906, 32.55154099315405, 32.53870899789035, 32.40154217928648, 31.987624941393733 ], "max_abs": 0.125, "relative_rmse": 0.007824343629181385, "equal_fraction": 0.22009055316448212 }, { "operator": "gemm", "variant": "q4_g32", "shape": [ 4096, 14336, 5376 ], "median_ms": 30.538500053808093, "min_ms": 29.95408303104341, "max_ms": 30.80308297649026, "samples_ms": [ 30.08712502196431, 29.95408303104341, 30.80308297649026, 30.737000051885843, 30.45966592617333, 30.538500053808093, 30.643749982118607 ], "max_abs": 1.1328125, "relative_rmse": 0.08104117959737778, "equal_fraction": 0.02208491787314415 }, { "operator": "gemm", "variant": "q4_g64", "shape": [ 4096, 14336, 5376 ], "median_ms": 29.812082881107926, "min_ms": 29.65637482702732, "max_ms": 30.311124864965677, "samples_ms": [ 29.684999957680702, 29.65637482702732, 29.743541963398457, 29.951457865536213, 29.812082881107926, 30.01641691662371, 30.311124864965677 ], "max_abs": 1.18359375, "relative_rmse": 0.09096471965312958, "equal_fraction": 0.019711222499608994 }, { "operator": "gemm", "variant": "q4_g128", "shape": [ 4096, 14336, 5376 ], "median_ms": 29.769500019028783, "min_ms": 29.42449995316565, "max_ms": 29.965666122734547, "samples_ms": [ 29.884499963372946, 29.42449995316565, 29.77370796725154, 29.965666122734547, 29.769500019028783, 29.60404218174517, 29.57754209637642 ], "max_abs": 1.32421875, "relative_rmse": 0.10005950182676315, "equal_fraction": 0.01792476326227188 }, { "operator": "sdpa", "variant": "query_chunk_0", "shape": [ 1, 4096, 56, 128 ], "median_ms": 24.146165931597352, "min_ms": 23.585624992847443, "max_ms": 24.465749971568584, "samples_ms": [ 23.585624992847443, 23.93633290193975, 24.196083890274167, 24.06216599047184, 24.146165931597352, 24.465749971568584, 24.197667138651013 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "sdpa", "variant": "query_chunk_128", "shape": [ 1, 4096, 56, 128 ], "median_ms": 41.21925006620586, "min_ms": 41.048833169043064, "max_ms": 41.29937500692904, "samples_ms": [ 41.06008284725249, 41.21925006620586, 41.29687510430813, 41.25925013795495, 41.29937500692904, 41.048833169043064, 41.09108285047114 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "sdpa", "variant": "query_chunk_512", "shape": [ 1, 4096, 56, 128 ], "median_ms": 26.095834095031023, "min_ms": 25.888917036354542, "max_ms": 26.268708053976297, "samples_ms": [ 25.888917036354542, 26.00116585381329, 25.939542101696134, 26.095834095031023, 26.154958875849843, 26.268708053976297, 26.120957918465137 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 }, { "operator": "sdpa", "variant": "query_chunk_1024", "shape": [ 1, 4096, 56, 128 ], "median_ms": 25.337791070342064, "min_ms": 25.203832890838385, "max_ms": 25.563500123098493, "samples_ms": [ 25.29804199002683, 25.253874948248267, 25.337791070342064, 25.203832890838385, 25.563500123098493, 25.462209014222026, 25.39620897732675 ], "max_abs": 0.0, "relative_rmse": 0.0, "equal_fraction": 1.0 } ] }