Baseten

@baseten

Inference is everything.

San Francisco and New York

固定
Baseten
@baseten
11月3日
Inference, training, routing, governance, and sandboxes are the building blocks of every AI product today. We’ve learned a lot from our customers about what it takes to build that system well: @OpenEvidence trains models that outperform the closed frontier, then serves them on
18
Baseten
@baseten
3時間
We built an inference engine for DeepSeek V4.1-Flash from scratch in Rust and CUDA. 4xB300: ~1,740 TPS decode 8xB300: ~2,060 TPS decode 1M-token prefill in ~12s It's open-source.
Phil Howes
@saltyph
8時間
we built an inference engine for deepseek v4.1-flash from scratch. the core engine is just rust + cuda. no pytorch, no sglang, no dsls, etc. ~1740 TPS decode on 4xB300, 2060TPS on 8xB300. 1M token prefill in ~12s. it's up on github
GIF
6
Baseten
@baseten
3時間
Honored to be #11 on the AI 100 list alongside so many of our friends and partners. Thank you, @BessemerVP!
Baseten
@baseten
9時間
What does the future of frontier AI look like? @polynoamial and @cHHillee tackle this question at All-Gather in “What’s ahead? The next era of frontier intelligence,” moderated by @saranormous. Nov 18, San Francisco. baseten.co/all-gather
1
Baseten
@baseten
11月10日
What’s the best harness for an open model on coding and agentic tasks? We partnered with @runta to investigate: 100B tokens and 26k trials later, the final results are coming in. Full report next week.
Guanlan Dai
@guanlan
11月10日
We’re spending up to 100B tokens across 26,040 agent runs to answer one question: when you switch models, should you switch harnesses too? Our v1.0 FrontierHarness leaderboard ranked harnesses on a single model. V1.1 expands it to 21 harnesses × 5 models × 62 tasks × 4
2

Baseten

Basetenさんのポスト