[Model] Support DeepSeek-V4.1-Flash (#56214)

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Signed-off-by: andyluo7 <andy.luo@amd.com>
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: andyluo7 <andy.luo@amd.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Yongye Zhu
2026-09-11 02:11:19 -07:00
committed by GitHub
co-authored by Jee Jee Li andyluo7 OpenAI Codex zjy0516 Claude Opus 5
parent e6821ceac9
commit e77daef89e
49 changed files with 3996 additions and 138 deletions
@@ -9,8 +9,13 @@ from vllm.model_executor.kernels.linear import (
_POSSIBLE_FP8_BLOCK_KERNELS,
_POSSIBLE_FP8_KERNELS,
_POSSIBLE_INT8_KERNELS,
_POSSIBLE_MXFP8_KERNELS,
_POSSIBLE_NVFP4_KERNELS,
)
from vllm.model_executor.kernels.linear.mxfp8.flashinfer import (
FlashInferCutedslMxfp8LinearKernel,
FlashInferCutlassMxfp8LinearKernel,
)
from vllm.model_executor.kernels.linear.nvfp4.base import (
NvFp4LinearKernel,
NvFp4LinearLayerConfig,
@@ -50,6 +55,8 @@ SUPPORTING = {
FlashInferFP8ScaledMMLinearKernel,
FlashInferCutlassNvFp4LinearKernel,
PerTensorTorchFP8ScaledMMLinearKernel,
FlashInferCutedslMxfp8LinearKernel,
FlashInferCutlassMxfp8LinearKernel,
}
@@ -60,6 +67,7 @@ def _all_kernel_classes() -> list[type]:
_POSSIBLE_FP8_BLOCK_KERNELS,
_POSSIBLE_INT8_KERNELS,
_POSSIBLE_NVFP4_KERNELS,
_POSSIBLE_MXFP8_KERNELS,
):
for kernels in registry.values():
for cls in kernels: