FlexGen is a high-throughput generation engine for running large language models with limited GPU memory (e.g., a 16GB T4 GPU or a 24GB RTX3090 gaming card!). This is a research project developed by HazyResearch@Stanford, SkyComputing@UC Berkeley, DS3Lab@ETH Zurich, CRFM@Stanford, and TogetherCompute.
Kategori: Uncategorized
PyGWalker: A Python Library for Exploratory Data Analysis with Visualization
PyGWalker can simplify your Jupyter Notebook data analysis and data visualization workflow. By turning your pandas dataframe into a Tableau-style User Interface for visual exploration.

Open Source ChatGPT Like
Open source solution replicates ChatGPT training process! Ready to go with only 1.6GB GPU memory and gives you 7.73 times faster training!

Tautan: https://www.hpc-ai.tech/blog/colossal-ai-chatgpt
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
This work presents Kornia – an open source computer
vision library which consists of a set of differentiable rou-
tines and modules to solve generic computer vision prob-
lems. The package uses PyTorch as its main backend both
for efficiency and to take advantage of the reverse-mode
auto-differentiation to define and compute the gradient of
complex functions. Inspired by OpenCV, Kornia is com-
posed of a set of modules containing operators that can be
inserted inside neural networks to train models to perform
image transformations, camera calibration, epipolar geom-
etry, and low level image processing techniques, such as
filtering and edge detection that operate directly on high
dimensional tensor representations. Examples of classical
vision problems implemented using our framework are pro-
vided including a benchmark comparing to existing vision
libraries.

Referensi
- https://arxiv.org/pdf/1910.02190.pdf
- https://github.com/kornia/kornia
- https://twitter.com/kornia_foss
PC Mainboard Schematics: Gigabyte
- Gigabyte GA-EG31M S2 Schematics
- Gigabyte GA-EP31 DS3L Schematics
- Gigabyte GA-G33M DS2R schematics
- Gigabyte GA-G31M S3L schematics
- Gigabyte GA-G31M S2L schematics
- Gigabyte GA-G31M ES2L schematics
Gigabyte GA-EG31M-S2
https://www.gigabyte.com/Motherboard/GA-EG31M-S2-rev-20
Gigabyte GA-EP31 DS3L
https://www.gigabyte.com/Motherboard/GA-EP31-DS3L-rev-10
GA-G33M-DS2R
https://www.gigabyte.com/Motherboard/GA-G33M-DS2R-rev-1x
GA-G31M-S3L
https://www.gigabyte.com/Motherboard/GA-G31-S3L-rev-1x
GA-G31M-S2L
https://www.gigabyte.com/id/Motherboard/GA-G31M-S2L-rev-10
GA-G31M-ES2L
https://www.gigabyte.com/id/Motherboard/GA-G31M-ES2L-rev-23/sp
Referensi
- 118b4_EP31-DS3L_Rev.1.0
- 798c0_G33M-DS2R_R101
- 2061c_G31-S3L_REV.1.1
- 509e1_G31M-S2L_R102
- 03d87_G31M-ES2L_R1.11
Bagaimana cara kerja ChatGPT

Tautan ke penjelasan ChatGPT menurut Stephen Wolfram https://writings.stephenwolfram.com/2023/02/what-is-chatgpt-doing-and-why-does-it-work
Perangkat Lunak Studi Literatur
Berikut ini beberapa perangkat lunak untuk membantuk studi literatur dalam penelitian
Bahasa Pemrograman Populer
Bahasa Pemrograman Populer menurut survey Stackoverflow tahun 2019 [tautan]

Belajar Penglihatan Komputer dari Prinsip Dasar
fdafda
Belajar dari prinsip dasar
Video di kanal youtube: :https://www.youtube.com/channel/UCf0WB91t8Ky6AuYcQV0CcLw/playlists
Daftar Slide: https://fpcv.cs.columbia.edu/Monographs
Daftar Slide
- “Introduction to Computer Vision,” Shree K. Nayar,
Monograph FPCV-0-1, First Principles of Computer Vision,
Columbia University, New York, Feb. 2022
[PDF] [bib] [©] - “Image Formation,”Shree K. Nayar,Monograph FPCV-1-1, First Principles of Computer Vision,Columbia University, New York, Feb. 2022[PDF] [bib] [©]
- “Image Sensing,” Shree K. Nayar,Monograph FPCV-1-2, First Principles of Computer Vision,Columbia University, New York, Feb. 2022[PDF] [bib] [©]
- “Binary Images,” Shree K. Nayar, Monograph FPCV-1-3, First Principles of Computer Vision,Columbia University, New York, Mar. 2022 [PDF] [bib] [©]
- “Image Processing I,”
Shree K. Nayar,
Monograph FPCV-1-4, First Principles of Computer Vision,
Columbia University, New York, Mar. 2022
[PDF] [bib] [©] - “Image Processing II,”
Shree K. Nayar,
Monograph FPCV-1-5, First Principles of Computer Vision,
Columbia University, New York, Mar. 2022
[PDF] [bib] [©] - “Edge Detection,”
Shree K. Nayar,
Monograph FPCV-2-1, First Principles of Computer Vision,
Columbia University, New York, May. 2022
[PDF] [bib] [©] - “Boundary Detection,”
Shree K. Nayar,
Monograph FPCV-2-2, First Principles of Computer Vision,
Columbia University, New York, Jun. 2022
[PDF] [bib] [©] - “SIFT Detector,”
Shree K. Nayar,
Monograph FPCV-2-3, First Principles of Computer Vision,
Columbia University, New York, Aug. 2022
[PDF] [bib] [©]
Tips pemakaian Wireshark
Ethernet frame mengandung CRC di bagian belakangnya. Di kebanyakan NIC (Network Interface Card), CRC dari ethernet ini tidak dikirim ke software aplikasi. Jika terjadi kesalahan pada CRC, maka frame tersebut dianggap rusak, jadi tidak dikirim sama sekali.
CRC di ethernet frame tidak muncul di wireshark, karena sudah dipotong di NIC
Referensi: https://osqa-ask.wireshark.org/questions/20862/how-to-display-the-packets-crc-in-the-gui-and-how-to-edit-crc-with-bad-value/
Paket IPv4 outgoing biasanya berisi checksum header 0000. Checksum ini akan diisi oleh hardware di layer fisik. Tujuannya untuk mengurangi beban komputasi di CPU. Checksum 0000 ini dianggap kesalahan oleh WireShark. Untuk tidak menampilkan pesan kesalahan, kita dapat disable pengecekan checksum IPv4. Default setting wireshark adalah tidak mengecek checksum di header IPv4.
Prosedur mengaktifkan/menonaktifkan header checksump IPv4 dapat dilihat di artikel https://packetlife.net/blog/2008/aug/23/disabling-checksum-validation-wireshark/