
- AvailableFPGA prototype
- In tape-out12 nm SoC
Unified Engine
An AI accelerator for LLMs, VLMs and VLA models at the edge. The FPGA prototype is ready for licensing and deployment.
We build the Unified Engine, an AI accelerator for edge devices, and the Apex GPU, which adds graphics to the same engine. Our 12 nm SoC, now in tape-out, is projected at 20× NVIDIA Jetson performance, under 10 W, at one-fifth the cost.

An AI accelerator for LLMs, VLMs and VLA models at the edge. The FPGA prototype is ready for licensing and deployment.

The Unified Engine with graphics, targeting Vulkan 1.4 and DirectX 12 Ultimate.
Apex Neural Rendering: frame generation, super resolution and ray reconstruction. Compare our frame generation with NVIDIA DLSS Frame Generation and register your interest in the product.
Graphics and AI on the Unified Engine.
The Apex GPU adds graphics to our AI accelerator. Graphics and compute run together on the same engine, with an open-source Mesa driver.

apex-compute/mesa
Separate from the Unified Engine FPGA board.
AI compute for edge devices.
An AI accelerator for LLMs, VLMs and VLA models at the edge. The FPGA prototype is ready for licensing and deployment.

Normalized to Jetson Orin Nano. Axelera and Apex FPGA measured on Llama 3.2 1B. SiMa.ai Modalix and Apex FPGA measured on Gemma 4 E2B. Jetson and Apex FPGA measured on Gemma 3 1B. The 12 nm simulation assumes 100 GB/s LPDDR5 bandwidth and 2 Apex Compute engines running in parallel. The 2-engine, 6 GB/s DDR bandwidth scenario is reproducible on FPGA with our GitHub releases.
M=K=N=1024, 42 GFLOPS BF16 peak. Reproduce with our GitHub releases
| Operation | GFLOPS | Of peak |
|---|---|---|
| BF16 matrix multiplication, A·Bᵀ | 40.17 | 95.6% |
| Matmul + bias + activation (GELU / SiLU) | 40.03 | 95.3% |
| Quantized matrix multiplication, BF16 × INT4/FP4 | 40.03 | 95.3% |
| Softmax fused into matrix multiplication | 37.76 | 89.9% |
| Memory-efficient attention kernel | — | ~90% |
| Streaming quantized matvec, decode mode | 31.33 | 74.6% |
Causal attention with bias enabled. Performance by sequence length, in GFLOPS. Peak: 36.87 GFLOPS, 87.8% of theoretical, at sequence length 3072 and head_dim 256.
A 256×2048 @ 2048×1024 matmul split 192/64 across two engines, recorded by the 8,192-timestamp trace buffer. Engine 1 finishes its smaller partition first and halts on the hardware synchronization flag until Engine 0 completes.
Engine 0 192×2048 @ 2048×1024
Engine 1 64×2048 @ 2048×1024
One compiled prefill program handles any prompt up to 192 tokens, and the instruction binary is 10× smaller.

INT4 or NVFP4 is selected for each 64-element K-block by minimizing MSE. Norms and embeddings stay BF16.

One command reflashes, warm-boots the fabric and re-scans PCIe. No power cycle, no host reboot.


Vision and navigation on-board, within a power budget that keeps the aircraft aloft.

Perception, fusion and planning with bounded latency, on the vehicle.

Vision-language and VLA models on-device. The whole policy stays on the robot.

For deployments where data cannot leave the building.
Memory-bandwidth-bound on weight matmul, compute-bound on SRAM operations, with no structural bottleneck in between. LPDDR5 gives about 10× the bandwidth of our current system.
Unified Engine FPGA board
An FPGA PCIe card with two Unified Engines, the XDMA driver, the Python runtime and a working Gemma 3 1B example. The package includes hardware design updates.

Send us the model and the power envelope.