Files
xc-llm-ascend/vllm_ascend/quantization
realliujiaxu 5093192769 [Bugfix] fix mtp profile run error where main model and mtp model use different quantization (#4102)
### What this PR does / why we need it?
In PR https://github.com/vllm-project/vllm-ascend/pull/3420, we
initially placed the quantization type (quant_type) in the MoECommMethod
class. However, since MoECommMethod follows a singleton pattern, it
couldn't accommodate scenarios where different layers in the model might
use different quantization approaches (e.g., MTP modules using
floating-point computation while the main model employs quantized
computation).
In this PR, we've moved the quantization type to the AscendFusedMoe
class and pass it as a parameter to MoECommMethod.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
```bash
export HCCL_BUFFSIZE=1024
export VLLM_VERSION=0.11.0

vllm serve /home/data/DeepSeek-R1_w8a8/ \
 --data-parallel-size 2 \
 --tensor-parallel-size 8 \
 --enable-expert-parallel \
 --served-model-name dsv3 \
 --max-model-len 32768 \
 --max-num-batched-tokens 4096 \
 --max-num-seqs 16 \
 --quantization ascend \
 --trust-remote-code \
 --gpu-memory-utilization 0.9 \
 --speculative-config '{"num_speculative_tokens": 2, "method":"deepseek_mtp"}'
```


- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: realliujiaxu <realliujiaxu@163.com>
2025-11-13 11:02:31 +08:00
..