[Docs] Fix stale W4A16 NVFP4 default kernel in ModelOpt docs (#59135)

Signed-off-by: Rajeev Warrier <warrier.rajeev.95@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Rajeev Warrier
2026-10-02 13:21:43 +00:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent d648847fe4
commit 30e956fad3
2 changed files with 4 additions and 6 deletions
+1 -3
View File
@@ -33,9 +33,7 @@ following `quantization.quant_algo` values:
`flashinfer_cutlass`, `flashinfer_cutedsl`, `flashinfer_trtllm`,
`flashinfer_cudnn`, and `marlin`; see `KernelConfig` on the
[Engine Arguments](../../configuration/engine_args.md) page and shown by
`vllm serve --help=KernelConfig`. For `W4A16_NVFP4`, `auto` currently
selects Marlin. Models with BF16 activations can explicitly select the
FlashInfer CuTe-DSL backend with `--linear-backend flashinfer_cutedsl`.
`vllm serve --help=KernelConfig`.
!!! note
For models quantized to MXFP8 with BF16 activations on SM100-family GPUs,