Custom HBM drives 5x LLM inference speed boost
BenBajarin · x · 2026-09-01
SK Hynix (SKHY) claims up to a 5.15x improvement in LLM inference performance using Custom HBM. The company is also exploring a new type of memory called Compute-using DRAM, which would allow DRAM to perform certain computations directly inside the memory itself, reducing the need to move data back and forth between memory and the processor.
More from Infra
- Inference optimization startup Wafer AI raises $40M Series A — ycombinator · 2026-09-02
- David Manheim: Cost Analysis of the Hugging Face Swarm Attack — davidmanheim · 2026-09-02
- Identical ComfyUI workflow on RX 9070 XT suddenly 3-5x slower, suspected ROCm VRAM eviction — bosox62 · 2026-09-02
- Token doubling is AI's Moore's law; interactive clock puts AI at 1% of US GDP by 2028 — robleclerc · 2026-09-02
- Sharon Zhou: As FLOPs get cheap vs HBM, algorithms will trade compute for memory — realSharonZhou · 2026-09-02
- Fleet runs GPU benchmarks in your browser, open-sources hundreds of WebGPU kernels — xenovatech · 2026-09-02