# usyd-fsalab/fp6\_llm

<https://repo.masters-masters.com/en/repos/usyd-fsalab/fp6_llm>

[Home](https://repo.masters-masters.com/en) › [usyd-fsalab](https://repo.masters-masters.com/en/owners/usyd-fsalab) › [fp6\_llm](https://repo.masters-masters.com/en/repos/usyd-fsalab/fp6_llm)

usyd-fsalab/fp6\_llm has 282 stars on GitHub. Its RepoMasters card: Alpha tier. An efficient GPU support for LLM inference with x-bit quantization (e.g…

| Field | Value |
| --- | --- |
| Owner | [usyd-fsalab](https://repo.masters-masters.com/en/owners/usyd-fsalab) |
| Stars | 282 |
| Forks | 26 |
| Language | [Cuda](https://repo.masters-masters.com/en/languages/cuda) |
| License | Apache-2.0 |
| Created | 2024 |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [usyd-fsalab/fp6\_llm](https://github.com/usyd-fsalab/fp6_llm) |

## Repository

An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).

The tier for repos with 250 to 699 ★. Published odds per card pulled: 20%. Rarity: Uncommon.

## Nearby in Cuda

- [facebookarchive/fbcuda · ★ 284 · Cuda · Alpha](https://repo.masters-masters.com/en/repos/facebookarchive/fbcuda)
- [leimao/CUDA-GEMM-Optimization · ★ 283 · Cuda · Alpha](https://repo.masters-masters.com/en/repos/leimao/CUDA-GEMM-Optimization)
- [NVIDIA-BioNeMo/nvMolKit · ★ 282 · Cuda · Alpha](https://repo.masters-masters.com/en/repos/NVIDIA-BioNeMo/nvMolKit)
- [nerficg-project/faster-gaussian-splatting · ★ 278 · Cuda · Alpha](https://repo.masters-masters.com/en/repos/nerficg-project/faster-gaussian-splatting)
- [ColfaxResearch/cutlass-kernels · ★ 271 · Cuda · Alpha](https://repo.masters-masters.com/en/repos/ColfaxResearch/cutlass-kernels)
- [LitLeo/OpenCUDA · ★ 269 · Cuda · Alpha](https://repo.masters-masters.com/en/repos/LitLeo/OpenCUDA)

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