[Mini-VLLM] Restore FlashInfer backend for FP8 KV on SM86

FlashInfer is the only backend serving fp8_e4m3 KV cache on compute
capability 8.6; the SM86 cut removed it and the Triton fallback
refuses FP8 KV, crashing worker startup. Restore flashinfer.py and
the triton_flashinfer shim.

Co-authored-by: Hinata
This commit is contained in:
2026-10-18 23:19:37 +07:00
co-authored by Hinata
parent c66baf3199
commit 7470a93875
2 changed files with 2816 additions and 0 deletions
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,22 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""Triton image-mask and FlashInfer causal attention composite."""
from vllm.v1.attention.backends.composite import (
MMPrefixAttentionRouting,
create_composite_attention_backend,
)
from vllm.v1.attention.backends.flashinfer import FlashInferBackend
from vllm.v1.attention.backends.triton_attn import TritonAttentionBackend
TritonFlashInferBackend = create_composite_attention_backend(
TritonAttentionBackend,
FlashInferBackend,
name="TritonFlashInferBackend",
backend_name="TRITON_FLASHINFER",
module=__name__,
routing_policy=MMPrefixAttentionRouting,
head_sizes=(256, 512),
kernel_block_sizes=(64,),
device_major=10,
)