AI ASICs — Products

Engine-synthesised product landscape for AI ASICs, ranked by trend signal across hiring, capital, orders, and discussion axes.

Last refresh: 2026-06-18.

Groq LPU inference appliance — AI inference accelerator

Trend: ↗ rising

Opportunity: Sovereign-AI demand outside US hyperscalers wants dedicated low-latency inference fabric.

Groq is the clearest pure-play inference-ASIC bet with a real sovereign deal anchor; hiring tilts into compilers and capital-markets (financing the buildout), not raw RTL — they have the chip, now they are scaling commercial+capex.

Companies committing: Groq.

AWS Trainium (Trainium / Trainium2 custom AI silicon) — AI accelerator (hyperscaler ASIC)

Trend: ↗ rising

Opportunity: Hyperscaler displacement of Nvidia GPUs with bespoke ASICs; Anthropic being pushed onto Trainium creates a guaranteed inference workload.

Trainium is the most-cited custom hyperscaler ASIC across demand chatter; Marvell is the locked-in design-services partner. Strong wind-direction product but most A1/A4 evidence sits inside AWS/Annapurna (not in the listed companies).

Companies committing: Marvell Technology, Inc.

Google TPU (custom hyperscaler ASIC) — AI accelerator (hyperscaler ASIC)

Trend: ↗ rising

Opportunity: Investor narrative shift toward profitable inference on custom ASICs vs renting Nvidia GPUs.

TPU is the canonical 'ASIC beats GPU' reference point in retail and investor discourse; Broadcom is the disclosed silicon partner monetizing it. Confirmed product-market fit; the public chatter is itself the trend signal.

Companies committing: Broadcom Inc.

AMD Instinct MI450 GPU — AI accelerator

Trend: → steady

Opportunity: Hyperscaler need for a credible second AI accelerator vs Nvidia (fact f953dea3-974f-4b3e-9c78-bdb57cb6a88f: 6 GW OpenAI commitment plus Oracle 50K MI450 line).

MI450 is the single most-anchored ASIC product in the evidence: two named hyperscale customers (OpenAI 6 GW, Oracle 50K) plus a $5B revolver and an explicit roadmap (MI300→MI325→MI350→MI430X→MI450). AMD is the strongest non-Nvidia bet in evidence.

Companies committing: AMD.

Cerebras Wafer-Scale / Condor Galaxy inference cluster — wafer-scale AI accelerator + inference cloud

Trend: → steady

Opportunity: Demand for >2,500 tok/s inference on frontier open models (fact 8bc85f5e: Llama 4 Maverick).

Cerebras is the only fully-stacked ASIC company in evidence with all five buckets covered: capex, anchor customer, US DC expansion, named inference products, and hiring an ASIC Architect to keep iterating. Strong hot signal.

Companies committing: Cerebras Systems.

Compiler / MLIR software stack for AI ASICs — ML compiler & runtime

Trend: → steady

Opportunity: Every ASIC needs a usable software story; fact b6ac96cb notes MLIR-based ML compiler skills are a recurring requirement.

The wedge that decides which AI-ASIC startup survives. Compiler hires are concentrated at the inference-pure-plays (Groq, Tenstorrent) — the moat is portability of HF/PyTorch workloads onto custom silicon, not silicon itself.

Companies committing: Groq, Tenstorrent, Cadence Design Systems.

Slim-Llama low-power LLM ASIC — edge LLM ASIC

Trend: · weak signal

Opportunity: Ultra-low-power on-device LLM inference (4.69 mW for 3B parameters) — pairs with the agentic / small-model trend in the cbr_post.

Research-stage but the demand-side narrative (efficient inference, agentic small models) is real. Watch-list opportunity; no commercial company in current evidence committed.

Microsoft Maia 200 AI accelerator — hyperscaler ASIC

Trend: · weak signal

Opportunity: Completes the 'Big-3 hyperscaler each with their own ASIC' picture (TPU / Trainium / Maia), validating the ASIC-over-GPU thesis.

Demand-narrative signal only; Microsoft not in the indexed company list so no A1/A4/A5 evidence. Important to track because it cements the structural shift away from merchant GPUs.