LLM Digest

Story

vllm_blog · Jul 23, 2026 · news

Source brief

Announcing vLLM AFD Plugin: Disaggregating Attention and FFN for Flexible MoE Serving

vllm.aiJul 23, 2026
original source linked

In brief

What vLLM AFD Plugin adds to the vLLM ecosystem: Attention–FFN disaggregation for MoE serving, GPU and Ascend NPU backends, connector-based execution, and graph and ubatching support.

Read the original at vllm.ai →Open in live feed Read that day’s brief

Announcing vLLM AFD Plugin: Disaggregating Attention and FFN for Flexible MoE Serving

Earlier in this thread 4 items

vLLM × HPC-Ops: High-Performance Attention and MoE Backends from Tencent Hunyuan

Kimi K3 vs DeepSeek V4 Pro vs GLM-5.2: Open Trillion-Scale MoE Models Compared on Benchmarks, License, and Serving Cost - MarkTechPost

vLLM x TileRT: Specialized Decode for Latency-Critical Serving

EAGLE-3 Speculative Decoding on AMD Instinct GPUs: Training and Serving with vLLM and AMD Quark