Run 01a0202b · KernelIndex

Primary measurement

16.5msmedian

Rank 2 in its comparison group · source-native comparison · observed 2025-06-27

Compare with #1 →

ms 20 15.045836448669434 · ms 50 16.456703186035156 · ms 80 16.761650466918944

Identity

implementationPyTorch

projectPyTorch

revisionunknown

workloadvocab = 128256 · hidden = 4096 · tokens = 1024 · bf16

comparison keysha256:3f155ea9555e4cf6…

sourceLiger-Kernel benchmarks

external iddistill_cosine_loss/forward/torch/nvidia-a100-sxm4-80gb/hidden4096-tokens1024-vocab128256-bf16/2025-06-27-09-20-34

sha256:f68ce6a876bcbf540e4bfbd…

Correctness

Marked passed by the source; the correctness policy was not published.

Workload

vocab128256

hidden4096

tokens1024

targetint64 [1024]

student_inputbf16 [1024, 2048]

teacher_inputbf16 [1024, 4096]

student_weightbf16 [128256, 2048]

teacher_weightbf16 [128256, 4096]

definition comparatornot_asserted

Measurements

latency · median16.5 ms

latency · p2015.0 ms

latency · p8016.8 ms

Protocol

harnessLiger-Kernel benchmark scripts

timercuda_events

primaryStatisticmedian

comparabilityFamilyliger_kernel_bench

Environment

gpuNVIDIA A100 (sm_80)

Artifacts

No artifacts published with this run.

Replications and notes

No attestations yet.

Community attestations. They never change the evidence level; only a KernelIndex-controlled rerun does.

Add a reproduction or note

Canonical manifest

Show manifest

{
  "run": {
    "kind": "BenchmarkRun",
    "spec": {
      "status": "passed",
      "timing": {
        "latencyNs": {
          "median": 16456703
        },
        "primaryStatistic": "median"
      },
      "observedAt": "2025-06-27T09:20:34.000Z",
      "measurements": [
        {
          "unit": "ns",
          "value": 15045836,
          "metric": "latency",
          "statistic": "p20"
        },
        {
          "unit": "ns",
          "value": 16761650,
          "metric": "latency",
          "statistic": "p80"
        }
      ],
      "sourceNative": {
        "source": "liger-kernel-bench",
        "metrics": {
          "ms_20": 15.045836448669434,
          "ms_50": 16.456703186035156,
          "ms_80": 16.761650466918944
        },
        "benchmark": "distill_cosine_loss/forward",
        "externalId": "distill_cosine_loss/forward/torch/nvidia-a100-sxm4-80gb/hidden4096-tokens1024-vocab128256-bf16/2025-06-27-09-20-34"
      },
      "protocolDigest": "sha256:a79eaf4df66c97c6adc1fb2d09df78682155d1ea86652ae0b70199875bde7747",
      "workloadDigest": "sha256:88ce4cf139b171c4dde8f7905153df3ff5ef235c7f81fee5d4dbfadfbe2569de",
      "environmentDigest": "sha256:90c9e2764222f592477cfccf3373519add5a1b881563956ad058c4f99e41b6b9",
      "implementationDigest": "sha256:8d3c47e7f80026f2aea3b6e664877bc71e2f9fd7bac39cbb81c7a4f47f6af064"
    },
    "metadata": {
      "name": "liger-distill-cosine-loss-forward-torch-nvidia-a100-sxm4-80gb-hidden4096-tokens1024-vocab128256-bf16",
      "title": "Chunked distillation cosine loss · torch · forward",
      "labels": {
        "liger_version": "0.5.10"
      }
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  },
  "protocol": {
    "kind": "BenchmarkProtocol",
    "spec": {
      "harness": {
        "name": "Liger-Kernel benchmark scripts",
        "repository": "https://github.com/linkedin/Liger-Kernel"
      },
      "measurement": {
        "timer": "cuda_events",
        "primaryStatistic": "median"
      },
      "comparability": {
        "notes": "Timed: the module forward pass, via triton.testing.do_bench with quantiles 0.5/0.2/0.8 (median with p20/p80 spread). The upstream CSV records no CUDA, driver, or torch version; the Liger release rides each run's labels. Comparable only within one kernel, workload, timed pass, and GPU.",
        "family": "liger_kernel_bench"
      }
    },
    "metadata": {
      "name": "liger-bench-do-bench-forward",
      "title": "Liger benchmark harness · forward pass"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  },
  "environment": {
    "kind": "ExecutionEnvironment",
    "spec": {
      "hardware": {
        "vendor": "nvidia",
        "product": "NVIDIA A100",
        "formFactor": "SXM4-80GB",
        "architecture": "sm_80"
      },
      "software": {}
    },
    "metadata": {
      "name": "liger-bench-nvidia-a100-sxm4-80gb",
      "title": "Liger benchmark host · A100-SXM4-80GB"
    },
    "apiVersion": "kernelindex.dev/v1alpha1"
  }
}

Cite this record (permalink, digest, access date)

Report an issue with this run

Published 2026-08-20 · Liger-Kernel benchmarks · BSD-2-ClauseAll results for Chunked distillation cosine loss →JSON