3 results found Sort:

PaddlePaddle
PaddleMIX PaddlePaddle
186
521
apache-2.0
23
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high per...
dit aigc clip sora llava sd-xl eva-clip qwen2-vl got-ocr20 internvl2 minicpm-v controlnet multimodal deepseek-vl ppdiffusers image-to-text text-to-image text-to-video stable-diffusion stablevideodiffusion
Created 2023-07-05
1,103 commits to develop branch, last one 22 hours ago
NetEase-Media
grps_trtllm NetEase-Media
7
113
apache-2.0
4
Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, d...
llm phi qwq qwen2 llama3 olmocr openai chatglm ai-agent qwen2-vl internvl2 janus-pro deepseek-r1 internvideo llama-index multi-modal tensorrt-llm function-call
Created 2024-08-21
144 commits to master branch, last one 21 hours ago
AXERA-TECH
ax-llm AXERA-TECH
14
85
bsd-3-clause
5
Explore LLM model deployment based on AXera's AI chips
llm vlm axera qwen2 gemma2 llama3 minicpm internvl2 minicpm-v huggingface transformer edge-computing
Created 2024-03-14
66 commits to prefill branch, last one 26 days ago