EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
1,101 Commits 3 Branches 0 Tags
646c1db5d707969307f0b7065a98d4cdd22a3949
Commit Graph

53 Commits

Author SHA1 Message Date
Mengqing Cao
6061f33670 [Bugfix][Model] Fix api in DeepSeek model (#545) 
### What this PR does / why we need it?
Fix api in DeepSeekV2, aligning with the latest code of the main branch
in vllm.

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
Test locally with deepseek-v2-lite, and will add CI by @Potabk.
Plz update the model UT after this pr is merged, thx! cc @Potabk

Signed-off-by: MengqingCao <cmq0113@163.com>
 2025-04-17 11:56:05 +08:00
Mengqing Cao
f6cf92e7d5 [quant][bugfix] fix deepseek quant bug (#478) 
see #465

Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: zzzzwwjj <1183291235@qq.com>
 2025-04-08 09:15:56 +08:00
Mengqing Cao
344228a5da [deepseek][bugfix] support deepseek quant (#469) 
- support deepseek quant
  - add w8a8_dynamic quant
see #391

Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: zzzzwwjj <1183291235@qq.com>
 2025-04-07 10:56:12 +08:00