meituan
/

DeepSeek-R1-Block-INT8

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

Resources

View closed (13)

量化类型

#21 opened about 1 month ago by

DeepSeek-V3-0324 int8 garbled

#20 opened about 1 month ago by

4-bits

#19 opened about 2 months ago by

Weight output_partition_size = 576 is not divisible by weight quantization block_n = 128

#18 opened 2 months ago by

Optimal `weight_block_size` for Intel AMX `amx_int8` `amx_tile`?

#17 opened 2 months ago by

what about `ollama`?

#16 opened 2 months ago by

是否有明确的sglang镜像版本推荐：）

#14 opened 2 months ago by

After deploying with the latest sglang, I found that the responses when calling the interface were chaotic.

#13 opened 2 months ago by