> booting the archive…
we use a small set of cookies. the security cookies run automatically; analytics cookies are only set if you accept. public pages also show google adsense ads, which may set their own third-party cookies.
> booting the archive…
ServiceNow turns a 15B reasoning model into a Mamba hybrid at 2.1x throughput. The interesting part is how they chose the distillation data.
Four markups, one tokenizer: TSX uses 94% more tokens than Pug. But the interesting cost is not where most developers expect it to be.
OpenAI's Ultrafast mode runs GPT-5.6 Sol at 750 tokens per second on Cerebras wafer-scale chips, 14x faster with no quality loss.
A reader said splintr beats gigatoken. After studying its benchmarks, the answer is nuanced: it wins on flexibility and latency, gigatoken on raw throughput.
Gigatoken is an MIT-licensed Rust tokenizer that encodes an 11.9 GB corpus at 24 GB/s — up to 989x faster than HuggingFace and 681x faster than tiktoken.