# vLLM cuts a DeepSeek V4.1 Engram lookup from 54 ms to 5.1 ms on eight MI355X GPUs

> Source: <https://runtimewire.com/article/vllm-deepseek-v41-engram-lookup-mi355x>
> Published: 2026-11-16 03:12:08+00:00

# vLLM cuts a DeepSeek V4.1 Engram lookup from 54 ms to 5.1 ms on eight MI355X GPUs

**Contributor Fangzhou Ai's 10.6x result covers a 589,824-row lookup against a 94 GiB shared table on eight MI355X GPUs, with the sort path enabled on ROCm from 32,768 rows.**

        By [RuntimeWire Staff](https://runtimewire.com/author/runtimewire-staff)
        · Published 

Fangzhou Ai, an AMD contributor filing as [\[email protected\]](https://runtimewire.com/cdn-cgi/l/email-protection#ec8a8d828b96848399c28d85ac8d8188c28f8381), traced a DeepSeek V4.1 prefill stall on MI355X to the order in which GPUs fetched rows from a host-resident table. The merged vLLM change cut the largest tested lookup from 54 ms to 5.1 ms by ordering those requests before they reached host memory.…
