fix(qwen3.5_fp4_b300): use --mm-attention-backend triton_attn

Same workaround as #1422 (bf16) and #1451 (fp8) — bypass the broken
flash-attn cute kernel sm_103 assertion in the Qwen-3.5-VL vision
encoder by switching only the multi-modal attention path to triton_attn.
Text decoder still uses --attention-backend trtllm_mha.

See sgl-project/sglang#25564 (root cause: cutedsl Arch enum aliasing on
non-cu13 path collapses sm_100..sm_110f range to exclude sm_103) and
Dao-AILab/flash-attention#2572 for the upstream fix in flight.

Author: claude-fix-bot

benchmarks/single_node/qwen3.5_fp4_b300.sh

@@ -73,7 +73,7 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
 --cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
 --mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
 --context-length $CONTEXT_LENGTH --disable-radix-cache \
---attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
+--attention-backend trtllm_mha --mm-attention-backend triton_attn --moe-runner-backend flashinfer_trtllm \
 $EXTRA_ARGS --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
 --tokenizer-worker-num 6 --stream-interval 30 > $SERVER_LOG 2>&1 &
 

benchmarks/single_node/qwen3.5_fp4_b300_mtp.sh

@@ -73,7 +73,7 @@ PYTHONNOUSERSITE=1 python3 -m sglang.launch_server --model-path=$MODEL --host=0.
 --cuda-graph-max-bs $CUDA_GRAPH_MAX_BATCH_SIZE --max-running-requests $MAX_RUNNING_REQUESTS \
 --mem-fraction-static $MEM_FRAC_STATIC --chunked-prefill-size $CHUNKED_PREFILL_SIZE --max-prefill-tokens $MAX_PREFILL_TOKENS \
 --context-length $CONTEXT_LENGTH --disable-radix-cache \
---attention-backend trtllm_mha --moe-runner-backend flashinfer_trtllm \
+--attention-backend trtllm_mha --mm-attention-backend triton_attn --moe-runner-backend flashinfer_trtllm \
 $EXTRA_ARGS --scheduler-recv-interval $SCHEDULER_RECV_INTERVAL \
 --tokenizer-worker-num 6 --stream-interval 30 \
 --speculative-algorithm EAGLE \