Ai-Inference

AI tools tagged Ai-Inference.

51 tools · handpicked & curated

// price

Alibaba Zhenwu V900 T-Head training and inference chip built for clusters of up to 500,000 units

NVIDIA RTX PRO 5500 Blackwell Blackwell workstation GPU with 84GB of ECC GDDR7 memory

Axelera Europa European in-memory-compute AI processor for edge and data-center inference

d-Matrix Raptor First 3D-DRAM accelerator, stacking compute directly on custom memory

Intel Crescent Island Intel's LPDDR5X inference GPU built for AI FLOPS per watt over raw graphics

Microsoft Maia 200 Microsoft's second-generation in-house inference chip for Azure

Cerebras CS-4 Wafer-scale inference system on Cerebras' new Nexus rack architecture

Meta MTIA 400 Meta chip that handles both AI training and ads-ranking inference

AMD Instinct MI440X MI400-series GPU for on-premise enterprise AI deployments

AMD Instinct MI455X Flagship MI400-series GPU built for AMD's Helios AI training rack

Alibaba Hanguang 800 Alibaba's first in-house AI inference chip

AMD Instinct MI325X High-memory CDNA 3 refresh for large-model inference

AMD Instinct MI450X CDNA 5 flagship of the MI400 series, built for the Helios rack

AWS Inferentia AWS's first custom inference chip

AWS Inferentia2 AWS's second-generation inference chip

Biren BR104 Half-size sibling of the BR100 for inference workloads

d-Matrix Corsair In-memory-compute chiplet card for low-latency LLM inference

Etched Sohu ASIC hardwired to run only transformer models

FuriosaAI RNGD Power-efficient second-generation inference chip

FuriosaAI Warboy FuriosaAI's first commercial inference chip

Google Coral Edge TPU Tiny USB and M.2 inference accelerator for embedded devices

Google TPU 8i Google's eighth-generation TPU, purpose-built for inference

Google TPU Ironwood (v7) Google's inference-optimized seventh-generation TPU

Google TPU v1 Google's first-generation inference-only TPU, never sold externally

Google TPU v5e Cost-efficient TPU generation for training and inference

Groq GroqCard Deterministic single-core language processing unit card

Groq LPU Language Processing Unit purpose-built for low-latency LLM inference

Huawei Ascend 310 Low-power edge inference chip

Intel Data Center GPU Flex 140 Low-power dual-GPU media and inference card

Intel Data Center GPU Flex 170 Media transcode and inference GPU for cloud workloads

Meta MTIA v2 Meta's in-house recommendation and ranking inference chip

NVIDIA A10 Ampere GPU for mixed graphics and AI inference

NVIDIA A10G AWS-favored Ampere GPU for graphics and inference

NVIDIA A30 Mainstream Ampere inference and analytics GPU

NVIDIA A40 Ampere data center GPU for graphics and inference

NVIDIA H20 Export-compliant Hopper GPU for the China market

NVIDIA H200 High-memory Hopper refresh for large-model inference

NVIDIA L4 Low-power Ada Lovelace inference GPU for cloud servers

NVIDIA L40S Ada Lovelace datacenter GPU for inference and graphics workloads

NVIDIA Rubin R100 Successor to Blackwell built for agentic-scale AI

NVIDIA Tesla P4 Low-power Pascal-era inference GPU

NVIDIA Tesla P40 Pascal-era inference GPU, still popular for cheap local LLM VRAM

NVIDIA Tesla T4 Ubiquitous low-power inference GPU

Qualcomm AI200 Rack-scale inference accelerator built on the Hexagon NPU

Qualcomm Cloud AI 100 Power-efficient datacenter inference card

Qualcomm Cloud AI 100 Ultra High-memory inference card for large generative models

SambaNova SN40L Reconfigurable dataflow chip for trillion-parameter inference

Samsung Mach-1 Samsung's first in-house AI inference chip

Tenstorrent Blackhole Tenstorrent's third-generation RISC-V AI accelerator

Tenstorrent Grayskull Tenstorrent's first commercial AI inference card

Tenstorrent Wormhole RISC-V-based scalable AI accelerator card