TT-NN is a Python & C++ Neural Network OP library.
| Release | Release Date |
|---|---|
| 0.60.0 | Jul 18, 2025 |
| 0.59.0 | Jun 18, 2025 |
| 0.58.0 | May 13, 2025 |
| 0.57.0 | Apr 15, 2025 |
| 0.56.0 | Mar 7, 2025 |
Last Update: June 23, 2025
Notes:
- ttft = time to first token | t/s/u = tokens/second/user | t/s = tokens/second; where t/s = t/s/u * batch.
- TP = Tensor Parallel, DP = Data Parallel; Defines parallelization factors across multiple devices.
- The reported LLM performance is for an input sequence length (number of rows filled in the KV cache) of 128 for all models except Mamba (which can accept any sequence length).
- The t/s/u reported is the throughput of the first token generated after prefill, i.e. 1 / inter token latency.
- Performance numbers were collected using the tt-metal model demos (accessible via the model links). If running with a vLLM inference server, performance may be different.
- * Blackhole software optimization is under active development. Please join us in shaping the future of open source AI!
[Discord] [Developer Hub]- For more information regarding vLLM installation and environment creation visit the Tenstorrent vLLM repository.
| Model | Batch | Hardware | ttft (ms) | t/s/u | Target t/s/u | t/s | TT-Metalium Release |
|---|---|---|---|---|---|---|---|
| Whisper (distil-large-v3) | 1 | n150 | 232 | 58.1 | 45 | 58.1 | v0.59.0-rc52 |
| Model | Batch | Hardware | Sec/Image | Target Sec/Image | Release |
|---|---|---|---|---|---|
| Stable Diffusion 1.4 (512x512) | 1 | n150 | 6.25 | 3 | |
| Stable Diffusion 3.5 Medium (512x512) | 1 | n150 | 16 | 10 |
Notes:
- Stable Diffusion sec/image is based on the time elapsed from submitting the input prompt to receiving the image from the VAE decoder.
| Model | Batch | Hardware | Image/sec | Target Image/sec | Release |
|---|---|---|---|---|---|
| ResNet-50 (224x224) | 16 | n150 | 4,700 | 7,000 | v0.59.0 |
| ResNet-50 (224x224) (DP=2) | 32 | n300 | 9,200 | 14,000 | v0.59.0 |
| ResNet-50 (224x224) (DP=8) | 128 | QuietBox | 35,800 | 56,000 | v0.59.0 |
| ResNet-50 (224x224) (DP=32) | 512 | Galaxy | 96,800 | 224,000 | v0.59.0 |
| ViT-base (224x224) | 8 | n150 | 1,370 | 1,800 | v0.60.0-rc4 |
| ViT-base (224x224) (DP=2) | 16 | n300 | 1,900 | 3,600 | v0.60.0-rc4 |
| ViT-base (224x224) (DP=8) | 64 | QuietBox | 7,700 | 14,400 | v0.60.0-rc4 |
| MobileNet-v2 (224x224) | 10 | n150 | 2,808 | 3,500 |
| Model | Batch | Hardware | Frame/sec (FPS) | Target FPS | Release |
|---|---|---|---|---|---|
| YOLOv4 (320x320) | 1 | n150 | 120 | 420 | |
| YOLOv4 (640x640) | 1 | n150 | 50 | 100 | |
| YOLOv8x (640x640) | 1 | n150 | 45 | 100 | |
| YOLOv8s (640x640) | 1 | n150 | 175 | 200 | |
| YOLOv8s_world (640x640) | 1 | n150 | 57 | 320 | |
| YOLOv9c (640x640) | 1 | n150 | 55 | 300 | |
| YOLOv10x (640x640) | 1 | n150 | 26 | 200 |
| Model | Batch | Hardware | Frame/sec (FPS) | Target FPS | Release |
|---|---|---|---|---|---|
| UNet - VGG19 (256x256) | 1 | n150 | 77 | 150 | |
| SegFormer Semantic Segmentation (512x512) | 1 | n150 | 84 | 300 | v0.60.0-rc4 |
| YOLOv9c (640x640) | 1 | n150 | 40 | 270 | |
| UFLD - v2 (320x800) | 1 | n150 | 1414 | 2000 |
| Model | Batch | Hardware | Sentence/sec | Target sentence/sec | Release |
|---|---|---|---|---|---|
| BERT-Large | 8 | n150 | 270 | 400 | |
| Sentence-Bert (backbone: bert-base) | 8 | n150 | 233 | 360 | v0.60.0-rc4 |
For the latest model updates and features, please see MODEL_UPDATES.md
For information on initial model procedures, please see Model Bring-Up and Testing
- Advanced Performance Optimizations for Models (updated March 4th, 2025)
- Programming Mesh of Devices (updated Sept 9th, 2024)
- ViT Implementation in TT-NN on GS (updated Sept 22nd, 2024)
- LLMs Bring up in TT-NN (updated Oct 29th, 2024)
- YOLOv4 Implementation in TT-NN on WH (updated November 8th, 2024)
- CNN Bring up & Optimization in TT-NN (updated Jan 22nd, 2025)
- Matrix Multiply FLOPS on Wormhole and Blackhole (updated June 17th, 2025)
TT-Metalium is our low-level programming model, enabling kernel development for Tenstorrent hardware.
Get started with simple kernels.
- Matrix Engine (updated Sept 6th, 2024)
- Data Formats (updated Sept 7th, 2024)
- Reconfiguring Data Formats (updated Oct 17th, 2024)
- Handling special floating-point numbers (updated Oct 5th, 2024)
- Allocator (Updated Dec 19th, 2024)
- Tensor Layouts (updated Sept 6th, 2024)
- Saturating DRAM Bandwidth (updated Sept 6th, 2024)
- Flash Attention on Wormhole (updated Sept 6th, 2024)
- CNNs on TT Architectures (updated Sept 6th, 2024)
- Ethernet and Multichip Basics (Updated Sept 20th, 2024)
- Collective Communication Library (CCL) (Updated Sept 20th, 2024)
- Blackhole Bring-Up Programming Guide (Updated Dec 18th, 2024)
- Sub-Devices (Updated Jan 7th, 2025)
- Matmul OP on a Single_core
- Matmul OP on Multi_core (Basic)
- Matmul Multi_core Reuse (Optimized)
- Matmul Multi_core Multi-Cast (Optimized)
A comprehensive tool for visualizing and analyzing model execution, offering interactive graphs, memory plots, tensor details, buffer overviews, operation flow graphs, and multi-instance support with file or SSH-based report loading. Install via pip or build from source:
pip install ttnn-visualizerThis repo is a part of Tenstorrent’s bounty program. If you are interested in helping to improve tt-metal, please make sure to read the Tenstorrent Bounty Program Terms and Conditions before heading to the issues tab. Look for the issues that are tagged with both “bounty” and difficulty level!
TT-Metalium and TTNN are licensed under the Apache 2.0 License, as detailed in LICENSE and LICENSE_understanding.txt.
Some distributable forms of this project—such as manylinux-compliant wheels—may need to bundle additional libraries beyond the standard Linux system libraries. For example:
- libnuma
- libhwloc
- openmpi (when built with multihost support)
- libevent (when built with multihost support)
These libraries are bound by their own license terms.