weichen 52aff9e229 [main] [bugfix] Fix misjudging quantized/unquantized scenarios (#2627) ...

### What this PR does / why we need it?
In a mixed-precision scenario, quant_config is not None, but MoE needs
to perform unquantized computation; however, quantized computation is
currently being used. Therefore, we put the with_quant logic into
forward, avoid misjudging in mix-precision scenarios.
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
e2e & ut

- vLLM version: v0.10.1.1
- vLLM main:
98ac0cb32d

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>

2025-08-29 16:20:22 +08:00

..

e2e

[main] [refactor] refactor fused_moe.py to enable token_dispatchers (#2570)

2025-08-28 10:13:35 +08:00

ut

[main] [bugfix] Fix misjudging quantized/unquantized scenarios (#2627)

2025-08-29 16:20:22 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00