2 min read
DeepSeek V4 Pro on AgentX: GB200 vs GB300 Rack-Scale Disaggregation
Both lean on PD disagg, GB300 adds DEP32 wide-EP decode, and the gap shows up in first-token latency rather than token rate
- agentx
- agentic
- benchmark
- +8
InferenceX Research
Articles
Benchmark write-ups on agentic inference, AgentX results, and chip and serving-stack economics.
New to the terminology? Browse the AI inference glossary.
Tagged “wide-ep”
4 articles
10 min read
GB300 NVL72 vs GB200 NVL72 Inference Performance & Perf per Dollar - on DeepSeek-V4-Pro 1.6T: Up to 2.83x Throughput
DSv4-Pro FP4 8K/1K, Dynamo+vLLM, disaggregated on both racks. GB300's 50% extra HBM (288 vs 192 GB/GPU) unlocks a wider prefill+decode recipe GB200 can't fit — lifting middle-of-curve perf/$ by 2.31x despite a 20% per-GPU TCO premium.
- benchmark
- gpu
- inference
- +9
8 min read
GB200 NVL72 vs B200 on DeepSeek R1 670B: Up to 4.4x Throughput per GPU at 125 tok/s/user
DeepSeek R1 FP4 1k/1k. NVL72's 72-GPU NVLink scale-up fabric lets decode run wide EP up to EP=32, where B200's 8-GPU NVLink island caps out at EP=8 over RoCEv2
- benchmark
- gpu
- inference
- +9
6 min read
GB200 NVL72 vs B200 on Kimi K2.5: 3.1x from Wide EP vLLM
Rack scale NVLink on NVL72 lets Dynamo vLLM run Kimi K2.5 wide EP up to Decode EP 16, taking peak throughput from 4,021 to 12,587 tok/s/GPU on 8k/1k NVFP4
- benchmark
- gpu
- inference
- +7