Loading activity…
@fireworksai_hq
The frontier platform for training and inference on open-weights models at scale.
Technology
Fireworks AI argues every serious AI team eventually builds its own data, evaluations and models, and maybe even chips.
AI
Fireworks AI named @BrendanFoody, @pirroh and @jefftangney as new speakers at Fireworks Forge.
AI
Fireworks says cache hits made up 60% of the bill in its DeepSWE comparison, with input tokens outnumbering output tokens 174 to 1.
Technology
DeepSeek says its KV cache, which lets the model reuse earlier calculations, needs a quarter of the high-bandwidth memory and an eighth of the SSD storage required by the previous generation's cache.
AI
Applied Compute CEO and other founders post about narrow AI models for business tasks.
