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

[Doc] Support kimi-k2-w8a8 (#2162)

Browse Source 
### What this PR does / why we need it?
In fact, the kimi-k2 model is similar to the deepseek model, and we only
need to make a few changes to support it. what does this pr do:
1. Add kimi-k2-w8a8 deployment doc
2. Update quantization doc
3. Upgrade torchair support list
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.10.0
- vLLM main:
9edd1db02b

---------

Signed-off-by: wangli <wangli858794774@gmail.com>
This commit is contained in:
Li Wang
2025-08-06 19:28:47 +08:00
committed by GitHub
parent 875a86cbe9
commit bf84f2dbfa
8 changed files with 194 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/ascend_config.py
View File

@@ -17,7 +17,7 @@ from typing import Optional
from vllm.logger import logger
TORCHAIR_MODEL_LIST = ["deepseek", "pangu"]
TORCHAIR_MODEL_LIST = ["deepseek", "pangu", "kimi_k2"]
def _check_torchair_supported(model_type: str):