OpenAI Jalapeño: Better than Nvidia Blackwell
1–10 of 390 posts
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#2This is most impressive. The interesting question to me, is outside of the LLM accelerator space: will generalized chips have massive leaps in performance once LLM technology is used to create the next generation? In general, will we see rapid advances while we extract the value of these models in creating architectures? I'm so far removed from the space that this is a very naive interpretation of all this, but I'm curious.
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#3Continued hardware improvements really make it hard for me to believe token prices will not continue to plummet.
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#4Why they don't research how to make their own RAM and they have to buy it from the common market?
They should GTFO with this crap.
Create barriers to computing for ordinary people while milking businesses for tokens.
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#5Continued hardware improvements really make it hard for me to believe token prices will not continue to plummet.
Token prices coming down means nothing if the models keep wasting them
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#6Why they don't research how to make their own RAM and they have to buy it from the common market? They should GTFO with this crap. Create barriers to computing for ordinary people while milking businesses for tokens.
Building a custom-designed ASIC is much easier than producing state of the art memory chips.
There's a reason why Micron and Nvidia are the crown jewels of American technology right now and for the foreseeable future.
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#7It's so funny to see FP4.... I remember 20 years ago being asked what sort of HPC we needed in genomics, and the answer was basically, "lower precision, faster" for the stuff I was working on. But FP4 is, well, almost comical.
One thing not on that comparison table: die size. If I'm understanding that correctly, it's about the same as the Rubin, but at 1/3 the number of NVFP4 PFLOPs. (The text disagrees with the table, I'm taking the table as truth, perhaps that's wrong...)
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#8Why they don't research how to make their own RAM and they have to buy it from the common market? They should GTFO with this crap. Create barriers to computing for ordinary people while milking businesses for tokens.
People keep saying stuff like this without understanding what it takes to make RAM. It's one of, if not the most, heavily patented things in the world. The second you dip your toes into those waters the lawsuits begin.
If somehow you get around the patent issues, you're now faced with huge research and development costs, fabs to build, processes to sort out and all of that has very high failure rates.
Last time I checked Micron was the largest patent holder in the world and even for them this is a hard area where they are number 3 in the market.
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#9Why they don't research how to make their own RAM and they have to buy it from the common market? They should GTFO with this crap. Create barriers to computing for ordinary people while milking businesses for tokens.
Building a custom-designed ASIC is much easier than producing state of the art memory chips. There's a reason why Micron and Nvidia are the crown jewels of American technology right now and for the foreseeable future.
NVIDIA produces memory?
Re: OpenAI Jalapeño: Better than Nvidia Blackwell
#10Why they don't research how to make their own RAM and they have to buy it from the common market? They should GTFO with this crap. Create barriers to computing for ordinary people while milking businesses for tokens.
Building a custom-designed ASIC is much easier than producing state of the art memory chips. There's a reason why Micron and Nvidia are the crown jewels of American technology right now and for the foreseeable future.
Nvidia does not make RAM