awesome-llama: https://github.com/RahulSChand/gpu_poor

ggml gpu huggingface language-model llama llama2 llamacpp llm pytorch quantization

Score: 8.340694647925071

Last synced: about 6 hours ago
JSON representation

Repository metadata:

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

• Host: GitHub
• URL: https://github.com/RahulSChand/gpu_poor
• Owner: RahulSChand
• Created: 2023-09-12T10:41:29.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-12-03T20:52:37.000Z (about 1 year ago)
• Last Synced: 2026-01-29T09:37:57.834Z (7 days ago)
• Topics: ggml, gpu, huggingface, language-model, llama, llama2, llamacpp, llm, pytorch, quantization
• Language: JavaScript
• Homepage: https://rahulschand.github.io/gpu_poor/
• Size: 1.56 MB
• Stars: 1,389
• Watchers: 6
• Forks: 86
• Open Issues: 8
• Metadata Files:
  • Readme: README.md

---

Owner metadata:

• Name: Rahul Shiv Chand
• Login: RahulSChand
• Email:
• Kind: user
• Description: B.E Computer Science BITS Pilani(2015-2019). Currently Research Fellow at Microsoft Research.
• Website:
• Location:
• Twitter:
• Company: RF @ Microsoft Research India
• Icon url: https://avatars.githubusercontent.com/u/16897807?u=cca34d1704716e1c6db3b57ec900b8ea33676e53&v=4
• Repositories: 1
• Last Synced at: 2023-06-28T07:02:26.804Z
• Profile URL: https://github.com/RahulSChand

---

GitHub Events

Total

• Fork event: 21
• Issue comment event: 4
• Issues event: 3
• Push event: 8
• Watch event: 231
• Total: 267

Last Year

• Fork event: 13
• Watch event: 135
• Total: 148

---

Committers metadata

Last synced: 9 days ago

Name	Email	Commits
Rahul Shiv Chand	c****0@g****m	49
rahulschand	c****0@g****m	8
Rahul Chand	r****d@R****l	8

---

Issue and Pull Request metadata

Last synced: about 2 months ago

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/RahulSChand/gpu_poor

---

---