InferenceX Research
Benchmark write-ups on agentic inference, AgentX results, and chip and serving-stack economics.
New to the terminology? Browse the AI inference glossary.
9 articles
10 min read
Jensen Sandbagging Performance Again, 2x more Annual Profit Per GigaWatt, The More you Buy, The More you Earn, AgentX, InferenceX, Extreme Co-Design
2 min read
Both lean on PD disagg, GB300 adds DEP32 wide-EP decode, and the gap shows up in first-token latency rather than token rate
2 min read
Where AMD’s vendor engine wins on performance per dollar, and what E2E Normalized Interactivity actually measures
2 min read
AMD’s vendor engine wins a real slice of the performance per dollar frontier, while Hopper struggles to serve K3 at all
3 min read
The Dynamo router becomes the bottleneck, no submission runs context parallelism, and AMD leaves KV offload on the table
17 min read
Can TileRT software on NVIDIA GPUs compete with Cerebras, Groq LPU, and SambaNova? Batch size 1, disaggregated engine, high-throughput prefill engine, high-interactivity decode engine
20 min read
Rubin LUT Based Tensor Core, Feynman, Rack Scale, Perf Per MegaWatt, Perf Per Dollar, Software Improvements, Public Rubin Software, PyTorch, vLLM, OpenAI Triton
29 min read
Day 0 Inference Performance, InferenceX, 100x performance improvement in 26 Days, Cost per Million Tokens, Huawei 950DT Inference Trace Analysis
10 min read
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.
