Sign in
← All awesome lists Search these repos

Awesome List

Awesome Chatgpt

A curated list of awesome LLM frameworks, libraries and software.

uhub/awesome-llm #ai #awesome #awesome-list #curated-list #large-language-models #list #llm #resources unsupported Unicode escape sequence LINE 218: ...6-10-17 10:54:20.809694+00:00'::timestamptz, '', E'[{"path"... ^ DETAIL: \u0000 cannot be converted to text. CONTEXT: JSON data, line 1: ... "dependency_count": 24, "dependencies": ["\u0000...
Open GitHub
List stars
862
README repos
1,021
Indexed repos
1,666
List commits
617
Forks
101
Open issues
21

Tracked list growth

GitHub stars and default-branch commits for uhub/awesome-llm.

Latest scan 2026-10-17 10:49

Likes history

GitHub stars

Commits history

Default branch commits

Indexed repositories

5 repos matching these filters.

Language: Cuda
Latest repo push 2026-10-17

Filter this list

Search within Awesome Chatgpt or narrow by ecosystem and project health.

Clear 1 refinement
Search mode
Tune results
More filters Topics, generated tags, stack, files, age, archive status, and growth.
Ecosystem
Files

Choose a suggestion or use commas to require multiple files.

Health

Uses known first-commit dates.

Momentum
Filters by observed commit-count growth over the repository's latest 7-day capture window. Repositories without a recent baseline are excluded.
Filters by observed GitHub star growth over the repository's latest 7-day capture window. Repositories without a recent baseline are excluded.
Reset filters
Highlighted

Open highlighted repo slot

Put your repository first

Promote a GitHub repo at the top of Awesome repository list views for 7 days.

karpathy/llm.c

LLM training in simple, raw C/CUDA

Stack
Cuda pip
Updated
2025-06-26
Lists
1 list mention
First commit
2024-04-08
License
MIT
Issues
224 open
Sign in to like karpathy/llm.c
30,938
stars
Forks
3,759
Commits
1,536 commits
Star growth, last 7 days
No 7-day history
Commit velocity, last 7 days
No 7-day history
GitHub
thu-ml/SageAttention

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

Stack
Cuda PEP 517 pip
GitHub topics
#attention #cuda #efficient-attention #inference-acceleration #llm #llm-infra
Updated
2026-01-17
Lists
1 list mention
First commit
2024-10-03
License
Apache-2.0
Issues
213 open
Sign in to like thu-ml/SageAttention
3,717
stars
Forks
504
Commits
188 commits
Star growth, last 7 days
No 7-day history
Commit velocity, last 7 days
No 7-day history
Website GitHub