Search: hazyresearch.stanford.edu | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

HipKittens: Fast and furious AMD kernels (hazyresearch.stanford.edu)

244 points

7 months ago

2.

Ask HN: Transformer alternatives that could have emergent properties when scaled

6 points

3 years ago

3.

GPUs Go Brrr (hazyresearch.stanford.edu)

1104 points

2 years ago

4.

We bought the whole GPU, so we're damn well going to use the whole GPU (hazyresearch.stanford.edu)

504 points

8 months ago

5.

From deep to long learning? (hazyresearch.stanford.edu)

499 points

3 years ago

6.

AMD GPUs Go Brrr (hazyresearch.stanford.edu)

268 points

7 months ago

7.

Look Ma, No Bubbles: Designing a Low-Latency Megakernel for Llama-1B (hazyresearch.stanford.edu)

236 points

a year ago

8.

How to scale LLMs better with an alternative to transformers (hazyresearch.stanford.edu)

156 points

3 years ago

9.

Batch computing and the coming age of AI systems (hazyresearch.stanford.edu)

123 points

3 years ago

10.

Learning From DNA: a grand challenge in biology (hazyresearch.stanford.edu)

119 points

2 years ago

11.

ThunderKittens: Simple, fast, and adorable AI kernels (hazyresearch.stanford.edu)

87 points

2 years ago

12.

Towards Interactive Weak Supervision with FlyingSquid (hazyresearch.stanford.edu)

75 points

6 years ago

13.

Long Convolutions via Polynomial Multiplication (hazyresearch.stanford.edu)

46 points

a year ago

14.

The Safari of Deep Signal Processing: Hyena and Beyond (hazyresearch.stanford.edu)

20 points

3 years ago

15.

Long-Context Retrieval Models with Monarch Mixer (hazyresearch.stanford.edu)

15 points

2 years ago

16.

Mind the Trust Gap: Fast, Private Local-to-Cloud LLM Chat (hazyresearch.stanford.edu)

11 points

a year ago

17.

Cartridges: Storing long contexts in tiny caches with self-study (hazyresearch.stanford.edu)

10 points

a year ago

18.

AMD GPUs Go Brrr (hazyresearch.stanford.edu)

9 points

7 months ago

19.

HipKittens: Fast and Furious AMD Kernels (hazyresearch.stanford.edu)

8 points

7 months ago

20.

ParallelKittens: Simple and Fast Multi-GPU AI Kernels (hazyresearch.stanford.edu)

7 points

7 months ago

21.

Software 2.0 and Data Programming: Lessons Learned, and What’s Next (hazyresearch.stanford.edu)

6 points

6 years ago

22.

HipKittens: Fast and Furious AMD Kernels (hazyresearch.stanford.edu)

4 points

7 months ago

23.

ThunderKittens update: Lots of new kernels, models and adorable kittens (hazyresearch.stanford.edu)

4 points

2 years ago

24.

ThunderKittens 2.0: Even Faster Kernels for Your GPUs (hazyresearch.stanford.edu)

3 points

3 months ago

25.

The Great American AI Race (hazyresearch.stanford.edu)

3 points

a year ago

26.

Long-Context Retrieval Models with Monarch Mixer (hazyresearch.stanford.edu)

3 points

2 years ago

27.

Monarch Mixer: Revisiting Bert, Without Attention or MLPs (hazyresearch.stanford.edu)

3 points

3 years ago

28.

ThunderKittens 2.0: Even Faster Kernels for Your GPUs (hazyresearch.stanford.edu)

3 points

3 months ago

29.

Linearizing LLMs with LoLCATs (hazyresearch.stanford.edu)

3 points

2 years ago

30.

Based: An Educational and Effective Sequence Mixer (hazyresearch.stanford.edu)

3 points

2 years ago