| { |
| "base_commit": "49e4b0f8fdf0ff508f7570c6b3ef3eada3c8747a", |
| "model_revision": "e10f2b1818813b45ca53a7c98d757f388368cedb", |
| "source": "Frozen implementation used for the October 2026 technical report", |
| "packaging_changes": [ |
| "Package-relative imports.", |
| "Convolution and recurrence retain independent cache dtypes.", |
| "CUDA runtime defaults to BF16 recurrent storage at every batch size; FP32 update accumulation is unchanged.", |
| "Physical-ring decode attention uses grouped zero-stride KV views with PyTorch EFFICIENT_ATTENTION to avoid observed cuDNN forward nondeterminism without duplicating persistent KV." |
| ], |
| "components": { |
| "b1_bf16_selected.py": { |
| "report_source_sha256": "82d7484627684ed3c2375a8d0339497399e67cf24ae705cddb45215cfe75f57d", |
| "release_sha256": "7c96b9fa282c87f094b0dfe174d6618a25d9df2c71bcae38812e4d36c711becd" |
| }, |
| "b1_bf16_fusions.py": { |
| "report_source_sha256": "9cd816ae32ee03e312445291dd859ff41b43acee94ee916de1e213db98d11a9b", |
| "release_sha256": "1ed5b969e0a14520d0692eea22aedc37477348328f796357bbee2b7b6c71361b" |
| }, |
| "b1_bf16_projection.py": { |
| "report_source_sha256": "dc82eeb0d13058f1e3aea7476f9c49b8bdbaaf733b27fac11078b97465551199", |
| "release_sha256": "dc82eeb0d13058f1e3aea7476f9c49b8bdbaaf733b27fac11078b97465551199" |
| }, |
| "b1_runtime_joint_projection.py": { |
| "report_source_sha256": "fba942060f0ceb84cb656e22a2a754c4e54f989617f34f176ab97094abac4876", |
| "release_sha256": "fba942060f0ceb84cb656e22a2a754c4e54f989617f34f176ab97094abac4876" |
| }, |
| "b1_bf16_crosslayer.py": { |
| "report_source_sha256": "0ee5c8984460cd2bafcef91223548ba5ee2f41c7ce1246550cad311b94b71efe", |
| "release_sha256": "0ee5c8984460cd2bafcef91223548ba5ee2f41c7ce1246550cad311b94b71efe" |
| }, |
| "b1_bf16_swa_prepare.py": { |
| "report_source_sha256": "ac91c6bfdafb59def4a552d13315ca3a69f5f45e4c5be348024a15cbb9b1ab73", |
| "release_sha256": "ac91c6bfdafb59def4a552d13315ca3a69f5f45e4c5be348024a15cbb9b1ab73" |
| }, |
| "b1_bf16_output_fusion.py": { |
| "report_source_sha256": "46b5702883b8d60ff824575e1c2af8d46a0f800e8148d89ec0a54087d75e6672", |
| "release_sha256": "46b5702883b8d60ff824575e1c2af8d46a0f800e8148d89ec0a54087d75e6672" |
| }, |
| "b512_share_bf16_weights.py": { |
| "report_source_sha256": "02677ef9d025423264c6b4a9bfaf85c82d5675aa74bf07de51d787f0699d9345", |
| "release_sha256": "02677ef9d025423264c6b4a9bfaf85c82d5675aa74bf07de51d787f0699d9345" |
| } |
| }, |
| "bf16_state_reference_run": "edgerock-128k-bestbatch-20261018-edge-bf16state-v3", |
| "physical_ring_attention_change": { |
| "source_diagnostic_run": "edgerock-bf16-runtime-grouped-sdpa-repeat-20261018-v16", |
| "release_inference_kernels_sha256": "564820a8692d5e9526040463b746e3cbc8b709c41b2e84f7188cdae60b067292", |
| "formal_acceptance": { |
| "status": "passed", |
| "date": "2026-10-18", |
| "run_id": "edgerock-bf16-runtime-acceptance-20261018-v17", |
| "slurm_job_id": 422927, |
| "environment": "H800; PyTorch 2.11.0+cu130; cuDNN 91900", |
| "reference": "Frozen source with external grouped EFFICIENT_ATTENTION correction; released candidate ran unwrapped. Equivalence is under this common corrected backend, not against historical nondeterministic cuDNN outputs.", |
| "checks": [ |
| "two independent reference/release process pairs per batch", |
| "token equality across implementations and within repeats", |
| "BF16 prefill and decode recurrent storage", |
| "independent per-request prefill", |
| "cache byte equality", |
| "original peak-memory tolerance", |
| "unwrapped release source" |
| ], |
| "speed_protocol": { |
| "input_tokens": 4096, |
| "output_tokens": 2048, |
| "full_generation_warmup_calls": 1, |
| "timed_calls": 3, |
| "metric": "output tokens / generation wall time including prefill", |
| "baseline": "original frozen default cuDNN path", |
| "release": "in-source grouped EFFICIENT_ATTENTION", |
| "paper_result": false |
| }, |
| "batches": { |
| "1": { |
| "manifest_sha256": "79b7a52fec334a62854e0ce6ccd4f9d623042736087be49e8fa2c742c4fb24c5", |
| "validation_passed": true, |
| "output_token_sha256": "851192f484b0dc2ba83232a381055637958c3fa4b69377320cc162b951321935", |
| "baseline_trials_output_tps": [ |
| 230.4101261568867, |
| 230.38532371553555, |
| 219.52501767745193 |
| ], |
| "release_trials_output_tps": [ |
| 210.74617372026032, |
| 210.7263298727412, |
| 203.97152321588845 |
| ], |
| "baseline_median_output_tps": 230.38532371553555, |
| "release_median_output_tps": 210.7263298727412, |
| "release_over_baseline": 0.9146690703828514, |
| "baseline_peak_allocated_gib": 14.269504070281982, |
| "release_peak_allocated_gib": 14.269504070281982, |
| "release_timed_tokens_repeatable": true, |
| "cache_bytes_equal": true |
| }, |
| "512": { |
| "manifest_sha256": "920d43855924e25521d1259908637528511e5a974bcd3382a777894f4d12e938", |
| "validation_passed": true, |
| "output_token_sha256": "ad1dd751ef4b468ea0f1183b2228655f173ca91fedcf45c6457305f597d71454", |
| "baseline_trials_output_tps": [ |
| 8270.370076665207, |
| 8272.754923447415, |
| 8233.773287549524 |
| ], |
| "release_trials_output_tps": [ |
| 8218.093798671816, |
| 8217.189832268046, |
| 8168.14852213838 |
| ], |
| "baseline_median_output_tps": 8270.370076665207, |
| "release_median_output_tps": 8217.189832268046, |
| "release_over_baseline": 0.9935697866112172, |
| "baseline_peak_allocated_gib": 63.54788160324097, |
| "release_peak_allocated_gib": 63.54788160324097, |
| "release_timed_tokens_repeatable": true, |
| "cache_bytes_equal": true |
| } |
| } |
| } |
| } |
| } |
|
|
