[CI] Upgrade vLLM to 20250919 (6d8246aa) and fix some broken issue (#2907)
### What this PR does / why we need it? 1. This pr bump vllm commit to6d8246aaff2. fix upstream changes https://github.com/vllm-project/vllm/pull/24548 abort multi-modal kwargs, make vllm main and `v0.10.2` both adaptable 3. fix metadata_builder changes introduced by https://github.com/vllm-project/vllm/pull/23693 4. fix `structured_outputs_config` changes introduced by https://github.com/vllm-project/vllm/pull/22772 5. fix `moe_config` changes introduced by https://github.com/vllm-project/vllm/pull/22537 Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: Yikun Jiang <yikunkero@gmail.com> - vLLM version: v0.10.2 - vLLM main:c60e6137f0--------- Signed-off-by: wangli <wangli858794774@gmail.com> Signed-off-by: MengqingCao <cmq0113@163.com> Co-authored-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
@@ -404,6 +404,10 @@ class AscendFusedMoEMethod(FusedMoEMethodBase):
|
||||
if hasattr(self.quant_method, "process_weights_after_loading"):
|
||||
self.quant_method.process_weights_after_loading(layer)
|
||||
|
||||
def get_fused_moe_quant_config(self, layer: torch.nn.Module):
|
||||
# TODO: implement this function
|
||||
pass
|
||||
|
||||
|
||||
class AscendEmbeddingMethod(AscendLinearMethod):
|
||||
"""Embedding method for Ascend quantization.
|
||||
|
||||
Reference in New Issue
Block a user