steve
@gpusteve
1.5K Following 6.1K Followers
why do inference providers HATE this man?
deepseek v4.1 flash now on @OpenRouter
pick @wafer_ai as your provider
(ss taken 9.12.26)
*overheard at 2nd street blue bottle*
larper 1: "bro Attention is All You Need is one of the most important papers in ai."
larper 2: "yes bro it's so good"
larper 1: "have you read it?"
larper 2: "no, have you?"
larper 1: "no"
don't be like these guys. pls read
Show more
who has actually read this paper? prob the most consequential paper in modern ai btw
stop larping and read it.
this is only the second resource in the ai performance engineering repo
imagine the ball knowledge in the other ones
Show more
you'll know more about inference than 90% of people if you fully understand this article
this is only the first resource in the ai performance engineering repo btw.
imagine the ball knowledge in the other ones
Show more
backflip for 5k. at 6k i go to japan 👀
Will do backflip if 5k is hit b4 5p today 😭😭😭
hiring exceptional engineers to join us at wafer.
our next mts will work across kernels, engines + serving and own customer workloads through prod
$200k-$300k + equity
sf, in person 5 days/week
link in comments
Show more
hiring for mts, growth, gtm, and chief of staff.
links in thread
i'm sad to announce that our recent fundraising round did not go according to plan...
we initially planned to raise $18m.
we didn't end up getting that number.
we ended up raising a $40m series a instead.
co-led by @MarathonMP and @chemistry, with participation from @Wing_VC, @AMD Ventures, @outsetcap, @fiftyyears, and @ycombinator, and our existing investors doubling down on @wafer_ai. we are also joined by an incredible list of angels, including @JeffDean (CEO, @DiscoLoopAI), @rauchg (CEO, @vercel), @andyfang (CTO, @DoorDash), @kvogt (CEO, Bot), @akothari (COO, @NotionHQ), @eastdakota (CEO, @Cloudflare), @deepgramscott (CEO, @DeepgramAI), and more.
back to the kernel mines
Show more
my team figured out how to run Kimi K3 on @AMD MI355X at 952 tok/s/node and 118 tok/s single stream.
3.8x the aggregate throughput/node and 1.3x the single stream decode of B200 and beat B300 on performance per dollar: 48 vs 33 tok/s/$
details in reply
Show more
