jbdalido Profile Banner
Jean-Baptiste Dalido Profile
Jean-Baptiste Dalido

@jbdalido

Followers
645
Following
2K
Statuses
1K

Engineering @zml_ai, fast motorcycles enthusiast

Paris, France
Joined November 2010
Don't wanna be here? Send us removal request.
@jbdalido
Jean-Baptiste Dalido
@jbdalido
3 days
RT @glcst: We are getting closer every day to delivering our new server architecture for Turso Cloud (f/k/a just Turso). It's shaping up g…
0
1
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
9 days
Ohhhhh. This is awesome!
@nanovms
NanoVMs
@nanovms
9 days
this week on the unikernel application spotlight we check out @zml_ai - run your inference with any model on any hardware (and yes the nanos unikernel has full native support for NVDIA gpus - both cloud && consumer models)
0
0
1
@jbdalido
Jean-Baptiste Dalido
@jbdalido
13 days
We're out of the woods! Only the start.
@zml_ai
ZML
@zml_ai
13 days
0
2
33
@jbdalido
Jean-Baptiste Dalido
@jbdalido
15 days
RT @steeve: "It doesn't matter what langage your write glue in, it's all in the GPU anyways. Python is fine." My dudes.
0
1
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
1 month
RT @steeve: Hey folks, what tool do you recommend for benchmarking an OpenAI compatible server? Is there a de facto standard?
0
2
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
1 month
RT @steeve: Here is a quick demo of @zml_ai running with MLX (cc @awnihannun). It's a very early demo and needs lots more work, but it's al…
0
4
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
2 months
RT @steeve: We can finally say it publicly: @poolsideai got their models running on @awscloud’s Trainium/Inferentia thanks to @zml_ai. No…
0
25
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
2 months
RT @steeve: We @zml_ai will be at Re:Invent all week, dm if you want to meet
Tweet media one
0
2
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
2 months
P o w e r
@steeve
Steeve Morin
@steeve
2 months
H200 go brrrr with @zml_ai's llmd
Tweet media one
0
0
4
@jbdalido
Jean-Baptiste Dalido
@jbdalido
3 months
RT @steeve: Holy shit we made it faster
Tweet media one
0
3
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
3 months
RT @steeve: So we're working on a custom async HTTP/1.1 server for the @zml_ai LLM serving stack. This is on a single thread, M3 Max. Uses…
0
2
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
4 months
@steeve @zml_ai Mammmmmmmamia
0
0
3
@jbdalido
Jean-Baptiste Dalido
@jbdalido
4 months
RT @steeve: We be cooking @zml_ai
Tweet media one
0
3
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
4 months
RT @renerocksai: #Zigtoberfest 2024 is over, and it was an absolute blast! I got to present @zml_ai, @croloris talked about Zine, David Sug…
0
3
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
4 months
RT @HotAisle: @zml_ai @steeve @Dell @AMD Just realized it was defaulting to CPU! While the Intel chips are pretty fast, we get much better…
0
2
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
4 months
RT @gawenr: Oops, I did it again.
0
1
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
5 months
RT @steeve: Join us!
0
4
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
5 months
RT @Roldiesel: Been waiting for this moment and great to see @zml_ai come out of stealth! Congratulations team! 👏🏼 #opensource #GenAI
0
2
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
5 months
RT @ylecun: ZML: a high-performance AI inference stack that can parallelize and run deep learning systems on lots of different hardware. I…
0
241
0
@jbdalido
Jean-Baptiste Dalido
@jbdalido
5 months
RT @eisokant: Excited to see this in the wild. In the coming years none of us will be thinking about what hardware we're running.
0
4
0