inference
-
SambaNova valuation reaches $11 billion as enterprise AI shifts
SambaNova reached an $11 billion valuation following a $1 billion Series F round to support its Reconfigurable Dataflow Unit architecture. The SN40L…
-
D-Matrix Corsair chip delivers 10x faster inference than NVIDIA
D-Matrix began shipping its Corsair digital in-memory compute hardware to hyperscalers and AI labs in June 2026. Led by Sid Sheth, the…
-
Groq LPU speed advantages for real-time finance
Groq LPU delivers 580 tokens per second for Llama 3.3 70B, significantly outperforming the 90 tokens per second from NVIDIA H100. This…
-
Cerebras WSE-3 vs SambaNova SN40L performance comparison
Cerebras runs Moonshot AI’s Kimi 2.6 trillion-parameter model at 981 tokens per second, outperforming the next-best GPU cloud provider by 6.7x. The…
-
SambaNova RDU scaling and composition-of-experts
SambaNova’s SN40L RDU achieves 132 tokens per second for Llama 3.1 405B while consuming only 10KW per rack. This power-efficient architecture uses…
-
How to get started with Replicate’s model hosting and GPU inference
Replicate offers over 1,000 community models with Nvidia T4 compute at $0.000225 per second. Startups can evaluate various providers like Runware for…
-
The people shaping Groq’s LPU revolution and silicon strategy
Groq’s LPU architecture achieves 241 tokens per second on Llama 2 70b, outperforming conventional GPUs. Following a $20 billion deal with NVIDIA,…
-
Llama 4 deployment priorities for local inference
Meta’s Llama 4 models offer efficient local enterprise deployment through mixture-of-experts architectures. Llama 4 Maverick outperforms GPT-4o and Gemini 2.0 Flash on…
-
Cerebras CS-3 vs SambaNova DataScale SN40L comparison
Cerebras generates 4,400 tokens per second on the GPT-OSS 120B model using a single CS-4 rack, significantly outperforming SambaNova’s 708 tokens per…
-
Deploying Mixtral 8x22B on Fireworks AI
Fireworks AI provides serverless GPU inference for the Mixtral 8x22B model, utilizing a sparse Mixture-of-Experts architecture with 141 billion parameters. Developers can…
-
Graphcore acquisition by SoftBank and AI chip inference performance
SoftBank acquired Graphcore amid reports of a $500 million deal following a 46 percent revenue drop. While SambaNova’s SN40L delivers up to…
-
Scaling inference with Positron and Intel hardware
Positron AI’s Atlas hardware delivers 70% faster inference and 66% lower power consumption than H100 setups. The upcoming Titan system utilizes Asimov…