{ "date": "2026-07-17", "runtime": "onnxruntime-web/webgpu 1.27.0", "source": { "bytes": 34647907, "sha256": "3612d5787ffb1026ae09bfd4a16b3379ea75fe0dd803484f7bb41645be6b6239" }, "gather_optimized": { "bytes": 34647902, "sha256": "53778e5b50d78ee55c8674d3d19f53de14da808bd1c231a9d4cebd5d44d3ad93", "fp32_intermediate_bytes_avoided": 29962240, "cpu_bit_exact": true, "webgpu_output_exact_tier_121": true, "webgpu_output_exact_tier_242": true, "accepted": true }, "fixed_kv": { "bytes": 34656423, "sha256": "6e3ae602fdebebe85f379ece1b24804ded32498ff94c950f7f1dda88423700f8", "cpu_bit_exact": true, "webgpu_output_exact": true, "accepted": false, "reason": "No in-place past-present buffer sharing in standard ONNX Runtime WebGPU; Slice and Pad offset the allocation benefit." }, "fp16_matmul_layers_1_2_3": { "bytes": 43622628, "sha256": "eef947f0eeb23c843f02d26c6abf6bc69d4cdde396b43846ca4802ec4810f9dc", "matmuls_rewritten": 21, "estimated_live_weight_bytes_avoided": 27131904, "webgpu_output_exact_tier_121": true, "webgpu_output_exact_tier_242": true, "isolated_peak_mib_baseline": 727.1, "isolated_peak_mib_candidate": 755.5, "accepted": false, "reason": "Measured isolated peak RSS regressed by 3.9 percent." } }