Edwin Mascarenhas @Kooledd

I like building fast computing systems. Deep Learning Architect @nvidia. Joined January 2010

Tweets

599
Followers

322
Following

423
Likes

58K

Edwin Mascarenhas @Kooledd

4 days ago

@IndiaToday @_anshuls @AneeshaMathur Activist. lol, every time I feel media can’t stoop lower than this you prove me wrong.

0 0 1 20 0

View Details

Edwin Mascarenhas @Kooledd

3 weeks ago

@BhattGantavya Yah!! Let’s work again together soon ;)

0 0 1 7 0

View Details

Ampere was the first GPU generation I worked on fresh out of undergrad doing perf work from simulator, RTL and silicon bring up! A lot of my key learnings came from this experience. A100 will always be close to my heart. Makes me very happy to see this :)

Silicon Data @Silicon_Data

4 weeks ago

As a gauge of AI compute demand, we like looking across the full cross-section of GPUs and the term structure. But if we have to pick a single favorite metric, it’s not the H100 rental rate — it’s the A100. Released in May 2020, this “ancient” chip is still going strong and

11 84 394 334K 242

1 0 0 209 0

View Details

Edwin Mascarenhas @Kooledd

3 weeks ago

@ndtv @rahulkanwal @ShivAroor @VishnuNDTV @PadmajaJoshi @Vasudha156 @SehgalRahesha @AdityaRajKaul @vedikas Didn’t realize you started doing jokes too, because this has to be a joke, right?

0 0 1 196 0

View Details

Edwin Mascarenhas @Kooledd

a month ago

🚀🚀🚀

Elon Musk @elonmusk

a month ago

SpaceX has committed to using Nvidia GPUs exclusively because they are the best

5K 7K 116K 10.2M 3K

0 0 3 1K 0

View Details

Edwin Mascarenhas @Kooledd

a month ago

@CNNnews18 @SmritiMishra22 Very 1984: Two minutes hate from the ministry of truth.

0 0 0 20 0

View Details

Edwin Mascarenhas @Kooledd

a month ago

@ShivAroor The dog whistle has been sounded and all of you have assembled for the witch-hunt. When are you going to pivot to real journalism for a change? What a sellout.

0 0 0 237 0

View Details

Edwin Mascarenhas @Kooledd

2 months ago

@TimesNow Priorities lol

0 0 0 16 0

View Details

Edwin Mascarenhas @Kooledd

2 months ago

@dpradhanbjp @RahulGandhi @INCIndia It’s better use of everyone’s time and tokens if you type your resignation instead of tweets and whataboutery.

0 0 0 14 0

View Details

Edwin Mascarenhas @Kooledd

2 months ago

“My CPU is a neural-net processor.” This almost aged well. Just missed the part where we’d run them on GPUs.

7 3 32 6K 3

View Details

Edwin Mascarenhas @Kooledd

3 months ago

@PMOIndia

0 0 1 32 0

View Details

Sarthak Sidhant @sidhant_sarthak

3 months ago

@cbseindia29 @EduMinOfIndia @PIB_Edu @PIB_India @AkashvaniAIR @airnewsalerts @DDNewslive @dpradhanbjp @sanjayjavin Can u please extend the deadline please because i was busy this week exposing you

132 2K 10K 290K 240

View Details

Edwin Mascarenhas @Kooledd

3 months ago

@petergyang Created symlink. My Claude.md is just a symlink to agents.md

0 0 0 17 0

View Details

Edwin Mascarenhas @Kooledd

3 months ago

@anjanaomkashyap Kids do better journalism than you, catch up.

0 0 0 38 0

View Details

Edwin Mascarenhas @Kooledd

3 months ago

@cbseindia29 Finally!!! Took you long enough and multiple pwnd instances to admit this.

0 0 0 51 0

View Details

Elon Musk @elonmusk

4 months ago

The GB300 is the best AI computer

NVIDIA @nvidia

4 months ago

Two frontier labs. One accelerated computing platform. Congrats to @SpaceX and @AnthropicAI on the new compute partnership, powered by 220,000+ NVIDIA GPUs inside Colossus 1. The future of AI runs on NVIDIA.

375 1K 13K 35.0M 1K

3K 4K 56K 34.2M 4K

View Details

Ben Pouladian @benitoz

4 months ago

Wow @SemiAnalysis just dropped day-zero numbers on @deepseek_ai V4 Pro Blackwell (B300): 8,075 tok/s/GPU AMD MI355X: 6.99 tok/s/GPU Hopper (H200): 186 tok/s/GPU at higher interactivity Same interactivity. ~1,000× the throughput per GPU vs MI355X. Blackwell also keeps serving all the way out to 80 tok/s/user, more than 2× the range where AMD flatlines That number isn’t a typo! But the throughput isn’t the story The story is the words “Day Zero” DeepSeek V4 Pro is a 1.6T-parameter Chinese frontier model. It dropped Friday. Shortly after, the open source community released day-0 deployment recipes, with NVFP4 checkpoints, TensorRT-LLM + WideEP, Dynamo, optimized V4 kernels in the pipeline That ecosystem doesn’t exist for the alternatives. That’s the real moat If you’re a neocloud operator, an enterprise AI buyer, or a hyperscaler sizing your next infrastructure build, this is what you’re actually buying when you buy NVIDIA You’re not buying a chip. You’re buying the guarantee that when the next frontier model drops, Chinese or American, open or closed, reasoning or multimodal, your fleet gets strong day-0 performance with continuous improvements over time I wrote about this four weeks ago in 27× On The Same Iron. MLPerf v6.0 showed GB300 delivering 2.7× more throughput than its v5.1 debut. Same silicon. Pure software. 60%+ cost-per-token reduction. Every operator already running Blackwell got that gain for free That was the proof point on installed-base compounding. This is the proof point on day-zero readiness for models that didn’t exist when you bought the iron Now look at the alternative You buy MI355X. The next frontier model drops. Now you wait. For AMD’s kernel team. For SGLang or vLLM upstream. For the open-source community to prioritize a stack that ships on a fraction of the world’s deployed compute. Weeks. Sometimes months. Sometimes never at peak Same story for any TPU buyer who isn’t Google. Same story for anyone betting on chip startups that haven’t earned a place in the open-source optimization queue Hopper, the last generation, is beating brand-new AMD silicon by a wide margin on a model that didn’t exist a week ago That’s not a benchmark. That’s a procurement decision Day zero is the moat $NVDA $AMD $GOOGL

26 37 337 1.3M 151

View Details

Edwin Mascarenhas @Kooledd

5 months ago

@LayoffAI You’re clearly double counting people over and over and artificially inflating the number for optics. Hypothetically - If a person switches employers ie transfer every year over 10 years you’re increasing the cumulative count by 10. It’s just the same 1 person 🤷