🤪
training and enjoying
interested in llm、infra、agent and benchmark
BIT CS | vibe developer | AI researcher | @Kimi
@PaddlePaddle @vllm-project @paperboytm
-
Beijing Institute of Technology
- Beijing, China
-
12:17
(UTC -12:00) - https://njx-njx.github.io/
- https://huggingface.co/NJX-njx
- @NJX_njx_ai
Highlights
Pinned Loading
-
vllm-project/semantic-router
vllm-project/semantic-router PublicIntelligent Mixture-of-Models Router for Efficient Heterogeneous LLMs Inference
-
vllm-project/vllm-ascend
vllm-project/vllm-ascend PublicCommunity maintained hardware plugin for vLLM on Ascend
-
Dao-AILab/flash-attention
Dao-AILab/flash-attention PublicFast and memory-efficient exact attention
-
nanoGPT
nanoGPT PublicForked from karpathy/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.





