[Model] Add LongCat-Flash (#3833)

### What this PR does / why we need it?
Add LongCat-Flash support.
### Does this PR introduce _any_ user-facing change?
N/A
### How was this patch tested?
CI passed

- vLLM version: v0.13.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: chuyuelin <923822139@qq.com>
Co-authored-by: chuyuelin <chuyuelin1@huawei.com>
This commit is contained in:
Chu Yuelin
2025-12-31 17:06:55 +08:00
committed by GitHub
parent 03679cf1d3
commit d07d8a4535
8 changed files with 79 additions and 14 deletions

View File

@@ -94,8 +94,6 @@ class AscendMultiHeadLatentAttention(MultiHeadLatentAttentionWrapper):
hf_config = get_current_vllm_config().model_config.hf_config
self.enable_shared_expert_dp = get_ascend_config(
).enable_shared_expert_dp
self.debug_layer_idx = int(self.prefix.split(".")[-2])
self.first_k_dense_replace = hf_config.first_k_dense_replace
self.tp_size = get_tensor_model_parallel_world_size()
self.layers = hf_config.num_hidden_layers
if mla_modules.indexer is not None: