Skip to content
KernelIndex
Search⌘K

flashinfer / wrapperc42e17

flashinfer_wrapper_c42e17 · flashinfer · python · Apache-2.0

Use it

Vendorable · source mirrored · Apache-2.0View source →

No package. Vendor the mirrored source: 25 lines, Apache-2.0, pinned at da91508.

main.py
curl "https://kernelindex.com/api/v1/implementations/flashinfer-flashinfer-wrapper-c42e17?include=source"
interfacepython
revisionda915083d4c7
symbolrun
pathmain.py
Compatibility
declared hardwareNVIDIA A100, NVIDIA B200, NVIDIA H100, NVIDIA H20, NVIDIA H200
architecturesunknown
dtypesfp32

Benchmark evidence

No published measurement for this revision.

No evidence · How evidence levels are derived →

Source and license

sourcehttps://huggingface.co/datasets/flashinfer-ai/flashinfer-trace
commitda915083d4c7c5e61aa3005e3d17ae488e0fc71c
revision digestsha256:62a646fa98c03fa6a5810f4e2ed318d0d8bc54219bd5238aa2f96d480ef4c36c
license declaredApache-2.0
license concludedApache-2.0
authorsflashinfer
imported2026-08-16

Kernel source

main.py25 lines
import torch
import flashinfer


def run(probs, top_p):
    batch_size, vocab_size = probs.shape
    device = probs.device

    assert vocab_size == 202048

    probs = probs.to(torch.float32)

    samples = flashinfer.sampling.top_p_sampling_from_probs(
        probs=probs,
        top_p=top_p,
        indices=None,
        deterministic=False,
        generator=None,
        check_nan=False
    )

    samples = samples.to(torch.int64)

    return samples

Source code from the importing source · Apache-2.0

No published measurement for this revision

JSON