Cost Effective Deployment of DeepSeek R1 with Intel® Xeon® 6 CPU on SGLang
DeepSeek R1's massive model size and unique MoE architecture normally requires many high-end AI accelerators to deploy; Intel PyTorch Team proposed a CPU-only solution at fractional cost as an alternative.
Existing CPU tools like llama.cpp processed MoE experts sequentially rather than in parallel, leading to substantially slower inference for large MoE models.
The optimized SGLang CPU backend achieves substantially faster LLM inference on Intel Xeon CPUs, with memory bandwidth efficiency of 85% for INT8 MoE and significantly reduced time-to-first-token and time-per-output-token compared to llama.cpp; the work has been upstreamed into the SGLang main branch.
Show all 13 reported metrics
Frequently asked questions
What did this team achieve with this AI workflow?
The optimized SGLang CPU backend achieves substantially faster LLM inference on Intel Xeon CPUs, with memory bandwidth efficiency of 85% for INT8 MoE and significantly reduced time-to-first-token and time-per-output-t…
What tools did this team use?
SGLang, Intel® Advanced Matrix Extensions (AMX), llama.cpp, PyTorch, AVX512, KTransformers.
What results were reported?
TTFT speedup vs llama.cpp (range across models): 6-14x; TPOT speedup vs llama.cpp (range across models): 2-4x; INT8 MoE memory bandwidth efficiency: 85%; effective memory bandwidth on MRDIMMs: 1.45TB/s (source-reported, not independently verified).
What failed first in this deployment?
Existing CPU tools like llama.cpp processed MoE experts sequentially rather than in parallel, leading to substantially slower inference for large MoE models.
How is this workflow AI workflow structured?
Prompt split into prefix and extend → Prefill via Extend Attention → Decode via Flash Decoding → MoE expert parallel computation → Multi-NUMA all-reduce synchronization.