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

[GLM-4.7] GLM Model support for GLM-Lite (#31386)

Browse Source 
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: Yuxuan Zhang <2448370773@qq.com>
This commit is contained in:
Yuxuan Zhang
2026-01-19 17:18:38 +08:00
committed by GitHub
parent 11bbf86f6a
commit 71832ba71e
9 changed files with 1135 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -112,6 +112,7 @@ _TEXT_GENERATION_MODELS = {
"GlmForCausalLM": ("glm", "GlmForCausalLM"),
"Glm4ForCausalLM": ("glm4", "Glm4ForCausalLM"),
"Glm4MoeForCausalLM": ("glm4_moe", "Glm4MoeForCausalLM"),
"Glm4MoeLiteForCausalLM": ("glm4_moe_lite", "Glm4MoeLiteForCausalLM"),
"GptOssForCausalLM": ("gpt_oss", "GptOssForCausalLM"),
"GPT2LMHeadModel": ("gpt2", "GPT2LMHeadModel"),
"GPTBigCodeForCausalLM": ("gpt_bigcode", "GPTBigCodeForCausalLM"),
@@ -465,6 +466,7 @@ _SPECULATIVE_DECODING_MODELS = {
"ExaoneMoeMTP": ("exaone_moe_mtp", "ExaoneMoeMTP"),
"LongCatFlashMTPModel": ("longcat_flash_mtp", "LongCatFlashMTP"),
"Glm4MoeMTPModel": ("glm4_moe_mtp", "Glm4MoeMTP"),
"Glm4MoeLiteMTPModel": ("glm4_moe_lite_mtp", "Glm4MoeLiteMTP"),
"MedusaModel": ("medusa", "Medusa"),
"OpenPanguMTPModel": ("openpangu_mtp", "OpenPanguMTP"),
"Qwen3NextMTP": ("qwen3_next_mtp", "Qwen3NextMTP"),