EngineX/xc-llm-kunlun
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[fix]update compressed-tensors scheme

Browse Source 
Deepseek v3.2 is supported now

Signed-off-by: Li Wei <liwei.109@outlook.com>
This commit is contained in:
Li Wei
2026-01-06 22:30:27 +08:00
parent 9c2b908908
commit 1c1b84d78c
4 changed files with 4 additions and 82 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_kunlun/ops/__init__.py
View File

@@ -21,8 +21,6 @@ import vllm_kunlun.ops.quantization.awq
import vllm_kunlun.ops.quantization.gptq
import vllm_kunlun.ops.vocab_parallel_embedding
import vllm_kunlun.ops.linear
# import vllm_kunlun.ops.quantization.kernels.scaled_mm.cutlass
import vllm_kunlun.ops.fused_moe.layer
import vllm_kunlun.ops.quantization.compressed_tensors.compressed_tensors
import vllm_kunlun.ops.quantization.compressed_tensors.compressed_tensors_moe
import vllm_kunlun.ops.quantization.kernels.scaled_mm.kunlun
import vllm_kunlun.ops.quantization.kernels.kunlun_scale_mm