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

[Model] Added GLM-4 series hf format model support vllm==0.6.4 (#10561)

Browse Source 
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
sixgod
2024-11-28 22:53:31 +08:00
committed by GitHub
parent 3ed5e73146
commit 5fc5ce0fe4
5 changed files with 30 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

@@ -48,6 +48,7 @@ _TEXT_GENERATION_MODELS = {
"FalconForCausalLM": ("falcon", "FalconForCausalLM"),
"GemmaForCausalLM": ("gemma", "GemmaForCausalLM"),
"Gemma2ForCausalLM": ("gemma2", "Gemma2ForCausalLM"),
"GlmForCausalLM": ("glm", "GlmForCausalLM"),
"GPT2LMHeadModel": ("gpt2", "GPT2LMHeadModel"),
"GPTBigCodeForCausalLM": ("gpt_bigcode", "GPTBigCodeForCausalLM"),
"GPTJForCausalLM": ("gpt_j", "GPTJForCausalLM"),
@@ -107,6 +108,7 @@ _EMBEDDING_MODELS = {
"XLMRobertaModel": ("roberta", "RobertaEmbeddingModel"),
"DeciLMForCausalLM": ("decilm", "DeciLMForCausalLM"),
"Gemma2Model": ("gemma2", "Gemma2EmbeddingModel"),
"GlmForCausalLM": ("glm", "GlmForCausalLM"),
"LlamaModel": ("llama", "LlamaEmbeddingModel"),
**{
# Multiple models share the same architecture, so we include them all