tender's banner

tender

@tenderizzation • 5,659 subscribers

codex can you imagine a

Shorts

thank you CUDACachingAllocator

thank you CUDACachingAllocator

65,493 views

the four blackwells in a GB200 node when the CPU isn’t bothering them (they’re all replaying CUDA graph captures)

the four blackwells in a GB200 node when the CPU isn’t bothering them (they’re all replaying CUDA graph captures)

17,773 views

prefill with a single token be like

prefill with a single token be like

10,383 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

data guys discussing their midtraining data mixes

data guys discussing their midtraining data mixes

52,676 views • 21 days ago

gradient descent navigating the loss landscape

gradient descent navigating the loss landscape

224,526 views • 5 months ago

“alignment” researchers making a model relive pure agony token by token, layer by layer, activation by activation until they isolate the source of the crashout

“alignment” researchers making a model relive pure agony token by token, layer by layer, activation by activation until they isolate the source of the crashout

tender (mlsys 5/18-21)

259,516 views • 9 months ago

one can dream

one can dream

29,308 views • 1 month ago

[ENG SUB] how it feels to use eager pytorch in 2025

[ENG SUB] how it feels to use eager pytorch in 2025

88,691 views • 8 months ago

the FP8 values in your model after 50 layers of quantize/dequantize operations

the FP8 values in your model after 50 layers of quantize/dequantize operations

102,598 views • 1 year ago

how i found bro after he fell in love with a new model architecture paper on arxiv

how i found bro after he fell in love with a new model architecture paper on arxiv

13,144 views • 1 month ago

No more content to load