Wang Kunpeng 859e861d92 [main][quantization] Support deepseek w4a8 per-channel quantization (#3011) ...

### What this PR does / why we need it?
1.Support deepseek w4a8 per-channel quantization
2.The eager mode supports converting weights to the NZ format
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
#### How to get weights using Modelslim

##### Installation steps

git clone https://gitcode.com/Ascend/msit.git
cd msit/msmodelslim
bash install.sh

##### Generate w4a8 per-channel weights

cd /example/DeepSeek
Command reference: msmodelslim/example/DeepSeek/README.md

- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9

---------

Signed-off-by: Wang Kunpeng <1289706727@qq.com>

2025-09-27 21:01:16 +08:00

..

test_quant_config.py

[3/N][Refactor][Quantization]remove packed_modules_mapping from models (#3021)

2025-09-19 20:50:14 +08:00

test_utils.py

[1/N][Refactor][Quantization] remove redundant quantizer class (#2680)

2025-09-04 11:35:14 +08:00

test_w4a8_dynamic.py

[main][quantization] Support deepseek w4a8 per-channel quantization (#3011)

2025-09-27 21:01:16 +08:00

test_w8a8_dynamic.py

[feat]: oproj tensor parallelism in pure DP and graph-mode scenarios. (#2167)

2025-09-07 10:31:32 +08:00

test_w8a8.py

[main] [refactor] refactor common_fused_moe.py (#2706)

2025-09-08 20:09:50 +08:00