# xlite-dev/Awesome-LLM-Inference

<https://repo.masters-masters.com/en/repos/xlite-dev/Awesome-LLM-Inference>

[Home](https://repo.masters-masters.com/en) › [xlite-dev](https://repo.masters-masters.com/en/owners/xlite-dev) › [Awesome-LLM-Inference](https://repo.masters-masters.com/en/repos/xlite-dev/Awesome-LLM-Inference)

xlite-dev/Awesome-LLM-Inference has 5,542 stars on GitHub. Its RepoMasters card: Stable tier. 📚A curated list of Awesome LLM/VLM Inference Papers with Codes…

| Field | Value |
| --- | --- |
| Owner | [xlite-dev](https://repo.masters-masters.com/en/owners/xlite-dev) |
| Stars | 5,542 |
| Forks | 443 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | GPL-3.0 |
| Created | 2023 |
| Topics | flash-attention, paged-attention, tensorrt-llm, vllm, awesome-llm, llm-inference, deepseek, flash-attention-3, deepseek-v3, minimax-01 |
| Tier | [Stable (5,000 to 19,999 ★)](https://repo.masters-masters.com/en/ranks/cult) |
| View on GitHub | [xlite-dev/Awesome-LLM-Inference](https://github.com/xlite-dev/Awesome-LLM-Inference) |

## Repository

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

The tier for repos with 5,000 to 19,999 ★. Published odds per card pulled: 0.9%. Rarity: Very rare.

## More repos by xlite-dev

- [xlite-dev/LeetCUDA · ★ 12,146 · Cuda · Stable](https://repo.masters-masters.com/en/repos/xlite-dev/LeetCUDA)
- [xlite-dev/lite.ai.toolkit · ★ 4,446 · C++ · RC](https://repo.masters-masters.com/en/repos/xlite-dev/lite.ai.toolkit)
- [xlite-dev/Awesome-DiT-Inference · ★ 594 · Python · Alpha](https://repo.masters-masters.com/en/repos/xlite-dev/Awesome-DiT-Inference)
- [xlite-dev/lihang-notes · ★ 512 · TeX · Alpha](https://repo.masters-masters.com/en/repos/xlite-dev/lihang-notes)
- [xlite-dev/torchlm · ★ 272 · Python · Alpha](https://repo.masters-masters.com/en/repos/xlite-dev/torchlm)
- [xlite-dev/HGEMM · ★ 158 · Cuda · Prototype](https://repo.masters-masters.com/en/repos/xlite-dev/HGEMM)

## Nearby in Python

- [HKUDS/ClawTeam · ★ 5,548 · Python · Stable](https://repo.masters-masters.com/en/repos/HKUDS/ClawTeam)
- [anishathalye/neural-style · ★ 5,547 · Python · Stable](https://repo.masters-masters.com/en/repos/anishathalye/neural-style)
- [volcengine/MineContext · ★ 5,542 · Python · Stable](https://repo.masters-masters.com/en/repos/volcengine/MineContext)
- [airbnb/knowledge-repo · ★ 5,541 · Python · Stable](https://repo.masters-masters.com/en/repos/airbnb/knowledge-repo)
- [kaifcodec/user-scanner · ★ 5,539 · Python · Stable](https://repo.masters-masters.com/en/repos/kaifcodec/user-scanner)
- [sapientinc/PRAXIST · ★ 5,537 · Python · Stable](https://repo.masters-masters.com/en/repos/sapientinc/PRAXIST)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.
