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 · Published

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.