biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Add LongCat-Flash (#23991)

Browse Source 
Signed-off-by: yangxurui <yangxurui@meituan.com>
Co-authored-by: yangxurui <yangxurui@meituan.com>
This commit is contained in:
XuruiYang
2025-09-25 12:53:40 +08:00
committed by GitHub
parent 90b139cfff
commit 845adb3ec6
31 changed files with 1357 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/registry.py
View File

@@ -109,6 +109,7 @@ _TEXT_GENERATION_MODELS = {
"Llama4ForCausalLM": ("llama4", "Llama4ForCausalLM"), # noqa: E501
# For decapoda-research/llama-*
"LLaMAForCausalLM": ("llama", "LlamaForCausalLM"),
"LongcatFlashForCausalLM": ("longcat_flash", "LongcatFlashForCausalLM"),
"MambaForCausalLM": ("mamba", "MambaForCausalLM"),
"FalconMambaForCausalLM": ("mamba", "MambaForCausalLM"),
"FalconH1ForCausalLM":("falcon_h1", "FalconH1ForCausalLM"),
@@ -287,6 +288,7 @@ _SPECULATIVE_DECODING_MODELS = {
"EagleDeepSeekMTPModel": ("deepseek_eagle", "EagleDeepseekV3ForCausalLM"),
"DeepSeekMTPModel": ("deepseek_mtp", "DeepSeekMTP"),
"ErnieMTPModel": ("ernie_mtp", "ErnieMTP"),
"LongCatFlashMTPModel": ("longcat_flash_mtp", "LongCatFlashMTP"),
"Glm4MoeMTPModel": ("glm4_moe_mtp", "Glm4MoeMTP"),
"MedusaModel": ("medusa", "Medusa"),
"Qwen3NextMTP": ("qwen3_next_mtp", "Qwen3NextMTP"),