Weiguo Liao

Weiguo's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in mlx-community/MiniMax-M2-4bit 2 months ago

how can I install mlx-lm version 0.28.4.

1

#3 opened 2 months ago by

Weiguo

New activity in mlx-community/Qwen3-Next-80B-A3B-Instruct-4bit 4 months ago

mlx-lm not ready

👍 5

12

#1 opened 4 months ago by

Weiguo

New activity in alskdgfjalkjf/gpt-oss-20b-base-Q8_0-GGUF 5 months ago

which llama.cpp version needed?

1

#1 opened 5 months ago by

Weiguo

New activity in Qwen/Qwen-7B-Chat over 2 years ago

Add support for flash-attention2

2

#3 opened over 2 years ago by

shigureui

有没有人写一个stream_chat，现在的体验有点差

🤝 👍 2

11

#6 opened over 2 years ago by

Weiguo

貌似很拉跨，一个7B的模型3090显存都不够载入，要是不安装它推荐的加速包，速度慢的像狗。

15

#12 opened over 2 years ago by

boxter007

BF16是不是依赖CUDA 11.7，我的机器是12.2

3

#7 opened over 2 years ago by

Weiguo

有没有人写一个stream_chat，现在的体验有点差

🤝 👍 2

11

#6 opened over 2 years ago by

Weiguo

BF16是不是依赖CUDA 11.7，我的机器是12.2

3

#7 opened over 2 years ago by

Weiguo

有没有人写一个stream_chat，现在的体验有点差

🤝 👍 2

11

#6 opened over 2 years ago by

Weiguo