@TileRT_AI

Tokens, in a blink.⚡️ Ultra-low latency inference. [email protected]

tilert.ai
Joined May 2026
  • Tweets18
  • Following3
  • Followers882
Ultra-High Interactivity on NVIDIA GPUs? TileRT InferenceX Can TileRT software on NVIDIA GPU compete with Cerebras, Groq LPU, SambaNova? Batch Size 1, Disaggregated engine, High throughput prefill engine, High interactivity decode engine newsletter.semianalysis.com/…

Ultra-High Interactivity on NVIDIA GPUs? - TileRT InferenceX

Can TileRT software on NVIDIA GPU compete with Cerebras, Groq LPU, SambaNova? Batch Size 1, Disaggregated engine, high throughput engine Prefill, high interactivity engine decode

newsletter.semianalysis.com
3
13
5
132
44,886
TileRT retweeted
jietang
@jietangMay 22
GLM-5.1-highspeed is coming, 400 tokens per second. Very expensive, but bring a new possibility.
41
25
12
599
55,187
Load more