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.
3 articles
3 min read
The Dynamo router becomes the bottleneck, no submission runs context parallelism, and AMD leaves KV offload on the table
2 min read
NVIDIA sweeps the 432B model, and the missing DP-attention points explain why cache locality became a routing constraint
12 min read
vLLM PR #36307 unlocks the trtllm-gen FP8 MoE kernel for MiniMax on B200; combined with NVFP4, perf/$ scales from 4.0x at 22 tok/s/user to 8.2x at 110 on 8K/1K
