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

[Multimodal][Speculative Decoding]Eagle3 mm support, enablement on qwen3vl (#29594)

Browse Source 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Signed-off-by: EanWang211123 <wangyiheng@sangfor.com.cn>
Co-authored-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
EanWang211123
2025-11-28 14:05:45 +08:00
committed by GitHub
parent c7ba1f6bc7
commit 37b15e97e8
5 changed files with 45 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/model_executor/models/registry.py
View File

@@ -414,6 +414,7 @@ _SPECULATIVE_DECODING_MODELS = {
"Eagle3LlamaForCausalLM": ("llama_eagle3", "Eagle3LlamaForCausalLM"),
"LlamaForCausalLMEagle3": ("llama_eagle3", "Eagle3LlamaForCausalLM"),
"Eagle3Qwen2_5vlForCausalLM": ("llama_eagle3", "Eagle3LlamaForCausalLM"),
"Eagle3Qwen3vlForCausalLM": ("llama_eagle3", "Eagle3LlamaForCausalLM"),
"EagleDeepSeekMTPModel": ("deepseek_eagle", "EagleDeepseekV3ForCausalLM"),
"DeepSeekMTPModel": ("deepseek_mtp", "DeepSeekMTP"),
"ErnieMTPModel": ("ernie_mtp", "ErnieMTP"),