Dylan PatelFounder and Chief Analyst, SemiAnalysis · The semiconductor-AI stack

Deepseek v4 hits InferenceX: Megakernel + Huawei ascend NPU tests

1 Jul 2026 · 0 min

Watch on YouTube

0:28

Cam, Kimbo, and Brian break down DeepSeek V4's performance on different hardware, including Huawei's Ascend NPU. They also weigh in on the VLLM versus SG Lang debate and discuss a new agentic benchmark in development.

On this week, we've got Cam, Kimbo, and Brian, and we are going to talk about everything InferenceX. The latest InferenceX article included a whole review about DeepSeek V4. We're going to talk about the model itself, the implementation, how it's running on different hardware, some of the nice VLLM versus SG Lang Twitter drama that's been going on, an agentic benchmark that we're working on, and, and yeah, lots of fun stuff. So guys, welcome to the show. Excited for this one.

More from Dylan

2:04

Even the frontier labs underestimated their own demand.

3d ago

1:52

The AI buildout needs more capital than backstops can cover.

4d ago

1:52

The fastest finish is not always the most efficient one.

4d ago

1:23:18

Ep. 037 - Who's Funding the $11 Trillion AI Buildout? (Capital Markets)

5d ago

0:48

"It's like a zombie apocalypse, but you don't know how many waves of zombies are coming."

5d ago

2:01

Open-source models are already taking the easier tasks. The bull case for frontier labs rests on one

1w ago

0:44

A $200 AI subscription can be worth $12,000 in tokens. Which plan delivers it is not close.

1w ago

50:14

Ep. 036 - Anthropic Subscriptions Beat OpenAI 5x, Depending on Your Workload (Tokenomics)

1w ago

0:39

What four weeks of SemiAnalysis consulting can do to a company

1w ago

34:41

Ep. 035 - Tech DD’s, Performance Projections, Supply Chain, Investment Thesis (Consulting)

1w ago

0:50

Are GPUs money printers?

1w ago

See all content