Julien from Baseten

506 posts

Julien from Baseten banner
Julien from Baseten

Julien from Baseten

@JulienTech

Growing @Basetenco: best-in-class model hosting for AI startups. Formerly @Stripe. NYC + SF. Let's talk GPUs, sales, or Brazilian jiu-jitsu.

New York City Beigetreten Şubat 2023
506 Folgt345 Follower
Julien from Baseten retweetet
Baseten
Baseten@baseten·
🚀 We’re excited to introduce our Speculative Decoding integration for our TensorRT-LLM Engine Builder! Our new integration allows engineers to: • Leverage SpecDec as part of our Engine Builder flow • Hit the ground running with pre-optimized configs • Lift the hood and tune for any custom use case 👉 Check out the launch blog to learn more: baseten.co/blog/speculati… Huge shoutout to our model performance team for this feature, including @aqaderb, Justin Yi, Bryce Dubayah, and @defpan!
English
0
7
21
2.5K
Julien from Baseten retweetet
Notable Capital
Notable Capital@notablecap·
Croissants + cloud infra really is the breakfast of champions 🥐 Had a great time hosting the AI/ML Engineering Leaders Breakfast Club this week with @baseten and @morganbarrettx in NYC.
Notable Capital tweet mediaNotable Capital tweet media
English
1
1
6
786
Julien from Baseten retweetet
Meridith McGraw
Meridith McGraw@meridithmcgraw·
A video of Trump’s call with RFK Jr. was leaked - Trump talks about vaccines, tells RFK Jr. doing something with him would be “big,” mentioned his call with Biden and said the bullet was like “the world’s largest mosquito.” RFK Jr apologized for the leak.
English
572
3.7K
9.8K
4M
Julien from Baseten retweetet
Baseten
Baseten@baseten·
After witnessing so many AI builders encounter the limitations of real-time inference, we’re excited to announce async inference on Baseten! 🔄 🎉 Check out our blog to learn more: buff.ly/4cGrDr1 And don't miss our live webinar on August 15th! buff.ly/3zEyLpn
Baseten tweet media
English
1
6
18
3.6K
Julien from Baseten retweetet
Tanay Kothari
Tanay Kothari@tankots·
If you’re building your own AI product, highly recommend working with @baseten Their customer support and expertise in AI infra is off the charts ❤️
English
3
7
48
8.2K
Julien from Baseten
Julien from Baseten@JulienTech·
Multi-model configuration is crucial for AI startups who break from the pack. Baseten's newest release makes it easier than ever. Pumped for Chains!
sarah guo@saranormous

almost all the winning applications we’ve seen this year have been “compound ai” now delivering multi-component, performant AI systems is 10X easier! @baseten chains ⛓️ is an example of how inference growing up will enable an incredible new generation of applications

English
0
0
4
241
Julien from Baseten
Julien from Baseten@JulienTech·
Getting coffee with an AI engineer from BrainPOP tomorrow and slowly realizing that none of my friends know what BrainPOP is. Did y'all not have a childhood!!??
English
0
0
1
128
Julien from Baseten retweetet
Baseten
Baseten@baseten·
Thank you to the ML engineers, scientists, and founders who attended our NYC AI breakfast yesterday morning. New York's community of AI leaders is just getting started!
Baseten tweet media
English
7
4
34
4.1K
Julien from Baseten retweetet
Baseten
Baseten@baseten·
We’re excited to launch Meta’s Llama 3 in our model library, in both 8B and 70B 🎉 The newly introduced Llama 3 is a significant improvement over Llama 2, with increased tokens, and reduced false refusal rates. These models deliver unparalleled performance, showcasing significant advancements in efficiency and speed. Our Llama 3 8B runs on A100s and Llama 3 70B runs on H100s, optimized for production.
English
7
22
233
131.4K
Julien from Baseten retweetet
sarah guo
sarah guo@saranormous·
It is an incredibly safe assumption that models get much cheaper and smarter from here, yet very few founders are acting like it
English
46
30
501
96.6K
Julien from Baseten
Julien from Baseten@JulienTech·
@baseten makes models go brrrrrr
Artificial Analysis@ArtificialAnlys

Baseten launches Mistral 7B API with leading performance 🚀 @baseten has entered the arena with their first serverless LLM offering of Mistral 7B Instruct. Artificial Analysis are measuring 170 tokens per second, the fastest of any provider, and 0.1s latency (TTFT) in-line with the next fastest provider. Mistral 7B Instruct from @Mistralai has become the leading 7B-class model for use-cases from RAG chatbots to data extraction. With pricing more than two orders of magnitude lower than large models like GPT-4 and Claude 3 Opus, models like Mistral 7B Instruct enable use-cases that wouldn’t be possible with the economics of larger models.

English
0
0
5
72
Julien from Baseten retweetet
Isaiah Granet
Isaiah Granet@zaygranet·
I have used a LOT of GPU providers. Hands down the most reliable one is @baseten They never have gone out for us, the team is always around, and the Truss system just…. makes sense…
English
0
3
19
2.5K
Sabina
Sabina@theesabina·
Went to go see the blue
Sabina tweet media
English
2
0
11
444
Julien from Baseten
Julien from Baseten@JulienTech·
@mschoening @mschoening this is sick. We'd love to know what you think of @baseten and get your feedback. Let me know if you want us to send over free credits. Excited to hear how the test goes!
English
0
0
0
54
Max Schoening
Max Schoening@mschoening·
OK, here we go...
Max Schoening tweet media
English
7
1
23
2.2K
Alex MacCaw
Alex MacCaw@maccaw·
We are here to stay! twitter.com/reflectnotes/s…
Reflect@reflectnotes

We're officially profitable! 🥳 Last year, we set a goal to become profitable by the end of 2023 – a milestone we have now successfully reached. What does this mean for Reflect? It means we're here for the long haul! Many startups rely on venture financing, pushing them into a "grow at all costs" model. We want to do things differently. Our aim is to grow sustainably and steady, building a useful product along the way. We are semi-bootstrapped, and the investors we do have are looking for dividends rather than an exit. Again, this aligns incentives towards sustainable growth that will give Reflect true longevity. It ensures that both product quality and the company will continue to thrive. In other words, your notes are safe with us. Our entire team wants to extend a heartfelt thank you to everyone who has supported us on this journey so far. We have lots of fun developments coming in the next few months and into 2024! 🫶 Thanks, Alex

English
51
2
413
54.5K
Philipp Tsipman
Philipp Tsipman@ptsi·
@meganreyno @jorgesancha @FinnMurphy12 @Bensign @auchenberg @sjwhitworth @bernhardsson @MikeMahlkow @cjbell_ @samseely @heikirk @bsideup @paulgb @ditzikow @bobbytables @jeansini @itunpredictable @inowland @morgantepell @RattrayAlex @StephWangBuilds @stevekrouse I’d definitely add @burkaygur @JulienTech @OlokobaYusuf to this “infra MVP” list :) And a bunch of great @huggingface @Nvidia folks bopping around My bet is NYC infra, like NYC AI, is gonna evolve different from SF. And that’s a great thing. Kudos to all :)
English
1
0
5
270

Entdecken

@aqaderb @defpan @baseten @MorganBarrettX @mprkhrst @theesabina @mschoening @OLLAMA