Hacker News: briggers

PyTorch Memory Tuning

briggers — Wed, 02 Aug 2023 06:45:54 +0000

Article URL: https://paulbridger.com/posts/pytorch-memory-tuning/

Comments URL: https://news.ycombinator.com/item?id=36967785

Points: 1

# Comments: 0

New comment by briggers in "Ask HN: Could you share your personal blog here?"

briggers — Tue, 04 Jul 2023 16:13:22 +0000

Machine learning productionization: https://paulbridger.com

PyTorch Performance Features and How They Interact

briggers — Thu, 29 Jun 2023 13:51:55 +0000

Article URL: https://paulbridger.com/posts/pytorch-tuning-tips/

Comments URL: https://news.ycombinator.com/item?id=36520381

Points: 3

# Comments: 0

New comment by briggers in "Ask HN: Is having a personal blog/brand worth it for you?"

briggers — Mon, 18 Jul 2022 13:39:59 +0000

Absolutely yes.

I write fairly deep ML performance tuning articles at https://paulbridger.com and the (many) hours I've spent on each article have been hugely worth it.

Many people reach out to me via this work, and when we talk they already see me as an expert or already want to work with me.

I need to blog more, thanks for the reminder.

New comment by briggers in "Ask HN: What bits of fundamental knowledge are productivity multipliers?"

briggers — Wed, 30 Mar 2022 13:19:30 +0000

Before you start optimizing runtime performance: measure, trace, inspect, or whatever is appropriate to understand current performance.

New comment by briggers in "Podman can transfer container images without a registry"

briggers — Tue, 15 Mar 2022 07:20:24 +0000

Perhaps you are looking for something like this?

docker run -d -p 5000:5000 --name registry registry:2

https://docs.docker.com/registry/#:~:text=The%20Registry%20i....

Wombo Dream: prompt-guided generative art

briggers — Mon, 17 Jan 2022 06:55:42 +0000

Article URL: https://app.wombo.art

Comments URL: https://news.ycombinator.com/item?id=29964035

Points: 2

# Comments: 0

Solving Machine Learning Performance Anti-Patterns: A Systematic Approach

briggers — Mon, 19 Jul 2021 10:57:20 +0000

Article URL: https://paulbridger.com/posts/nsight-systems-systematic-optimization/

Comments URL: https://news.ycombinator.com/item?id=27881132

Points: 54

# Comments: 1

Solving Machine Learning Performance Anti-Patterns: A Systematic Approach

briggers — Mon, 28 Jun 2021 15:40:48 +0000

Article URL: https://paulbridger.com/posts/nsight-systems-systematic-optimization/

Comments URL: https://news.ycombinator.com/item?id=27663309

Points: 10

# Comments: 2

New comment by briggers in "Reloadr – Hot code reloading tool for Python"

briggers — Fri, 05 Feb 2021 13:46:39 +0000

I used to love doing this with Clojure, it’s an awesome way to increase productivity by a good chunk.

It’s less about saving the time to re-run something, and more about removing conceptual overhead (I think).

Analyzing the performance of Tensorflow training on M1 Mac Mini and Nvidia V100

briggers — Thu, 14 Jan 2021 07:04:42 +0000

Article URL: https://wandb.ai/vanpelt/m1-benchmark/reports/Can-Apple-s-M1-help-you-train-models-faster-cheaper-than-NVIDIA-s-V100---VmlldzozNTkyMzg

Comments URL: https://news.ycombinator.com/item?id=25773109

Points: 226

# Comments: 91

Object Detection at 2530 FPS with TensorRT and 8-Bit Quantization

briggers — Sun, 03 Jan 2021 12:53:18 +0000

Article URL: https://paulbridger.com/posts/tensorrt-object-detection-quantized/

Comments URL: https://news.ycombinator.com/item?id=25621480

Points: 9

# Comments: 0

Optimizing models using the PyTorch JIT

briggers — Mon, 28 Dec 2020 01:21:11 +0000

Article URL: https://lernapparat.de/jit-optimization-intro/

Comments URL: https://news.ycombinator.com/item?id=25555837

Points: 1

# Comments: 0

New comment by briggers in "A terminal-based workflow for research, writing, and programming"

briggers — Fri, 04 Dec 2020 11:04:45 +0000

Yes! I do this and love it. Works locally or via SSH with no difference at all.

Mastering TorchScript: Tracing vs. Scripting, Device Pinning, Graph Modification

briggers — Sat, 21 Nov 2020 13:05:14 +0000

Article URL: https://paulbridger.com/posts/mastering-torchscript

Comments URL: https://news.ycombinator.com/item?id=25169493

Points: 7

# Comments: 0

Mastering TorchScript: Tracing vs. Scripting, Device Pinning, Graph Modification

briggers — Fri, 30 Oct 2020 12:46:12 +0000

Article URL: https://paulbridger.com/posts/mastering-torchscript/

Comments URL: https://news.ycombinator.com/item?id=24941642

Points: 7

# Comments: 0

New comment by briggers in "Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream"

briggers — Mon, 19 Oct 2020 01:08:33 +0000

Nice one! I've long been interested in the ONNX serving path.

New comment by briggers in "Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream"

briggers — Sun, 18 Oct 2020 14:44:02 +0000

Yeah. A 2080Ti doesn't fit in your pocket or in your AR glasses but the same techniques and tools scale down.

New comment by briggers in "Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream"

briggers — Sun, 18 Oct 2020 14:41:53 +0000

BTW, this is pumping the same video file through the network - not just a single file. I don't measure latency, but this is not a deep pipeline so it's easy to calculate.

New comment by briggers in "Object Detection at 1840 FPS with TorchScript, TensorRT and DeepStream"

briggers — Sun, 18 Oct 2020 13:11:26 +0000

Mobile phones definitely since these days most of them have pretty powerful GPUs.