xlite-dev

icon indicating a website link https://github.com/xlite-dev

icon location China icon location Develop ML/AI toolkits and ML/AI/CUDA Learning resources.

Results 4 repositories owned by xlite-dev

Awesome-LLM-Inference

4.9k
Stars
330
Forks
4.9k
Watchers

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

verified publisher icon xlite-dev

Awesome-DiT-Inference

478
Stars
24
Forks
478
Watchers

📚A curated list of Awesome Diffusion Inference Papers with Codes: Sampling, Cache, Quantization, Parallelism, etc.🎉

verified publisher icon xlite-dev

flux-faster

24
Stars
0
Forks
24
Watchers

A forked version of flux-fast that makes flux-fast even faster with cache-dit, 3.3x speedup on NVIDIA L20.

verified publisher icon xlite-dev

ffpa-attn

242
Stars
12
Forks
242
Watchers

🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.

verified publisher icon xlite-dev