Trendingby GlyphInference chips
Peak · emerged April 2017 · high December 2025 · +3% on the month before · 352 mentions on Trending in 14 days
Accelerators built to serve models cheaply and fast rather than to train them: TPUs, LPUs, wafer-scale and custom silicon. Named by Jouppi et al., Google: In-Datacenter Performance Analysis of a Tensor Processing Unit (Apr 16, 2017). Also called AI accelerators, AI chips, NPU, LPU, Custom silicon.
Index 0 to 100, monthly
Signals
Hacker News stories, last 12 months256 stories, +0% on the 12 months before
arXiv papers, last 12 months96 papers, +81% on the 12 months before
Wikipedia views, October 202613,074, -24% on a year beforeGitHub repositories1,310Funding rounds naming it13, $6.6B in all| Signal | Reads as | |
|---|---|---|
| Hacker News stories, last 12 months256 stories, +0% on the 12 months before | 256 stories, +0% on the 12 months before | Adoption |
| arXiv papers, last 12 months96 papers, +81% on the 12 months before | 96 papers, +81% on the 12 months before | Adoption |
| Wikipedia views, October 202613,074, -24% on a year before | 13,074, -24% on a year before | Decline |
| GitHub repositories1,310 | 1,310 | Adoption |
| Funding rounds naming it13, $6.6B in all | 13, $6.6B in all | Adoption |
Trending terms
| Term | PeakPeak score | ||
|---|---|---|---|
| Sep 32 months ago | 1 | 19 | |
| Aug 312 months ago | 1 | 17 | |
| Aug 252 months ago | 1 | 19 |
Companies
GitHub projects
1,310 repositoriesSemiAnalysisAI/InferenceXOpen Source AI Accelerator Research Platform Standard / 开源推理研究平台xLLM-AI/xllmA high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundakendryte/nncaseOpen deep learning compiler stack for Kendryte AI accelerators ✨FeSens/openTPUAn open-source AI accelerator, developed by AI: RTL, ISA, simulator, compiler and profiler in one repo. Runs Qwen3, LFM2.5 and Qwen3.5 on a InfiniTensor/InfiniTensorInfiniTensor is a high-performance inference engine tailored for GPUs and AI accelerators. Its design focuses on effective deployment and swfacebookresearch/deepfloatAn exploration of log domain "alternative floating point" for hardware ML/AI accelerators.
| Name | Stars | |
|---|---|---|
| SemiAnalysisAI/InferenceXOpen Source AI Accelerator Research Platform Standard / 开源推理研究平台 · Jul 12, 2025 1 year ago | Jul 12, 20251 year ago | 1,956 |
| xLLM-AI/xllmA high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Founda · Aug 12, 2025 1 year ago | Aug 12, 20251 year ago | 1,613 |
| kendryte/nncaseOpen deep learning compiler stack for Kendryte AI accelerators ✨ · Apr 4, 2018 8 years ago | Apr 4, 20188 years ago | 899 |
| FeSens/openTPUAn open-source AI accelerator, developed by AI: RTL, ISA, simulator, compiler and profiler in one repo. Runs Qwen3, LFM2.5 and Qwen3.5 on a · Sep 24, 2026 6 weeks ago | Sep 24, 20266 weeks ago | 880 |
| InfiniTensor/InfiniTensorInfiniTensor is a high-performance inference engine tailored for GPUs and AI accelerators. Its design focuses on effective deployment and sw · Jul 27, 2022 4 years ago | Jul 27, 20224 years ago | 566 |
| facebookresearch/deepfloatAn exploration of log domain "alternative floating point" for hardware ML/AI accelerators. · Sep 27, 2018 8 years ago | Sep 27, 20188 years ago | 401 |
Funding
13 rounds| Name | Amount | |
|---|---|---|
| Oct 19, 20263 weeks ago | $1,500M | |
| Jul 8, 20264 months ago | $1,000M | |
| Sep 17, 20251 year ago | $750M | |
| Aug 18, 20262 months ago | $700M | |
| Aug 5, 20242 years ago | $640M | |
| FuriosaAIGrowth · Oct 29, 2026 11 days ago | Oct 29, 202611 days ago | $620M |
| Jan 13, 202610 months ago | $500M | |
| Feb 24, 20268 months ago | $350M |
Partnerships
| Name | |
|---|---|
| Apr 14, 20266 months ago |
Related movements
Local AIRunning language and image models on your own laptop, phone or server instead of a cloud API.Mixture of expertsModels split into many expert blocks with only a few active per token, so they grow in size without growing in cost.
| Movement | Stage |
|---|---|
| Local AIRunning language and image models on your own laptop, phone or server instead of a cloud API. | Peak |
| Mixture of expertsModels split into many expert blocks with only a few active per token, so they grow in size without growing in cost. | Peak |
History
Tracking started: emerged April 2017, peak, 5 other names recorded
| Date | What changed |
|---|---|
| Sep 24, 2026 | Tracking started: emerged April 2017, peak, 5 other names recorded |
Sources: Curve: Hacker News story titles, Wikipedia pageviews and arXiv papers by month, refreshed Nov 1, 2026. Related entities from the other Glyph Ibis sources' public APIs, matched by name. How stages work.