Top Tweets for #InferCon
Disaggregated serving, reinforcement learning, and the marriage of hardware + software.
Our CEO Nikola Borisov got into all three on the #INFERCON main stage with @nvidia and @Datadoghq

@ayirpelle @o_lacombe @Google @datadoghq you documented #infercon like a champ - thanks for being there π
Went to #InferCon today, was awesome getting to listen to and chat with the teams from @modal, @nvidia, and @gimletlabs!
Much more exciting stuff coming soon, stay tuned π

you can tell it was an intense panel because i spent most of the time with my head down, staring intently into space and contemplating system design
silver lining: that meant i was hardcore repping my new @sgl_project hat

Few things learned today at #infercon:
- agentic traffic represents 90%+ of all traffic for most of the providers (@morphllm, @FireworksAI_HQ), we see that @munitoai too
- as a consequence kv cache is more and more important and should be treated as first class citizen
- as a consequence storage and networking technology is racing in prices after gpus (ai gets everything expensive)
- most of the cool folks out there already have some versions of compilers/self improving loops on inference
- @datadoghq does have some cool swag


@datadoghq #Infercon on reusing evals, shared penalty between SFT and RL, hesitation tokens @nebiusai @hanrui_w
On November 23 at 9 a.m. PT, Iβll join my colleagues to share what weβre learning about making large models faster to serve, improving them through post-training, and building agents that can handle longer tasks reliably. Weβll also talk about the problems weβre still trying to solve and where weβd like to collaborate with university researchers.
Weβll introduce the Nebius PhD Fellowship, which gives PhD students funding, GPU compute, and the chance to work directly with our research teams. If youβre working on one of these problems or advising someone who is, Iβd love to hear what youβre exploring.
Register for Inside Nebius Research on November 23 at 9 a.m. PT
https://t.co/mftMtDKcHh
Apply for the Nebius PhD Fellowship by January 15, 2027
https://t.co/cU3DGMf3Dt

@datadoghq #Infercon @spirinus @nvidia GPUs are βpdfβ, productive, durable, fungible, @simon_mo_ @inferact invoked multiple times

the re-occurring theme.
CI/CD and evals have become more important than ever.
#InferCon

Latency and cost decide whether open models work in production. That's the work we do every day at Inco.
Today @zhijianliu is on the KV cache panel at #InferCon, 10:55am in Room B. If you're there, go catch it.
Infer/Con is today π§‘
10:55am, Room B: our co-founder @zhijianliu is on the "KV Cache as a Distributed Systems Problem" panel at #InferCon, convened by @datadoghq.
At the speaker lunch, he's also hosting a lunch table on speculative decoding and inference for agents. Come join us!

On the KV cache panel at #InferCon today: 10:55am, Room B, with Nick Khami and Charles Frye.
We'll get into when to keep, move or drop the cache, and how long-running agents change the math.
At lunch I'm hosting a founders' table on speculative decoding and inference for agents.
Infer/Con is today π§‘
10:55am, Room B: our co-founder @zhijianliu is on the "KV Cache as a Distributed Systems Problem" panel at #InferCon, convened by @datadoghq.
At the speaker lunch, he's also hosting a lunch table on speculative decoding and inference for agents. Come join us!

Infer/Con is today π§‘
10:55am, Room B: our co-founder @zhijianliu is on the "KV Cache as a Distributed Systems Problem" panel at #InferCon, convened by @datadoghq.
At the speaker lunch, he's also hosting a lunch table on speculative decoding and inference for agents. Come join us!

Our CEO & cofounder @simon_mo_ is speaking at #InferCon on November 16 in San Francisco, convened by #Datadog!
Building AI systems? Join us to explore inference, infrastructure, and operating AI at scale.
Apply to attend: https://t.co/sV0v3NOCcA

Inco AI is heading to Infer/Con in San Francisco on Nov 16th, 2026, convened by #Datadog!
Our co-founder @zhijianliu is speaking at #InferCon, alongside researchers and engineers building AI systems and tackling the challenges of inference at scale. Building with open models or working on inference? Letβs connect and swap notes on latency, cost, and scaling AI systems.
Apply at https://t.co/wRpWjwwy5S

@gmi_cloud Inference workloads are reshaping the data center. Looking forward to Jun's panel at #InferCon.
Data centers are being redesigned to meet the demands of AI inference.
Our Chief AI Officer Jun will join the panel "The Future of Data Centers" at #InferCon on Monday, Nov 16, stay tuned!
Speaking at INFER/CON on Nov 16 in SF, convened by @datadoghq. Joining the conversation on the future of AI data centers and running inference at scale. Come say hi π https://t.co/Xjfiph3ksE #INFERCON #Datadog

Most Popular Users

Elon Musk 
@elonmusk
240.6M followers

Barack Obama 
@barackobama
118.7M followers

Cristiano Ronaldo 
@cristiano
114.5M followers

Donald J. Trump 
@realdonaldtrump
111.9M followers

Narendra Modi 
@narendramodi
107M followers

Rihanna 
@rihanna
98.7M followers

NASA 
@nasa
92.2M followers

Justin Bieber 
@justinbieber
91.8M followers

KATY PERRY 
@katyperry
90M followers

Taylor Swift 
@taylorswift13
84M followers

Lady Gaga 
@ladygaga
75.5M followers

Virat Kohli 
@imvkohli
73.4M followers

Kim Kardashian 
@kimkardashian
70.8M followers

YouTube 
@youtube
68.7M followers

Neymar Jr 
@neymarjr
66.4M followers

Bill Gates 
@billgates
65.2M followers

Selena Gomez 
@selenagomez
63.1M followers

The Ellen Show
@theellenshow
62.1M followers

CNN 
@cnn
61.7M followers

X 
@x
60.6M followers




























