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

[Model] Support for fairseq2 Llama (#11442)

Browse Source 
Signed-off-by: Martin Gleize <mgleize@meta.com>
Co-authored-by: mgleize user <mgleize@a100-st-p4de24xlarge-4.fair-a100.hpcaas>
This commit is contained in:
Martin Gleize
2025-01-19 19:40:40 +01:00
committed by GitHub
parent 81763c58a0
commit bbe5f9de7d
7 changed files with 197 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -47,6 +47,7 @@ _TEXT_GENERATION_MODELS = {
"DeepseekV3ForCausalLM": ("deepseek_v3", "DeepseekV3ForCausalLM"),
"ExaoneForCausalLM": ("exaone", "ExaoneForCausalLM"),
"FalconForCausalLM": ("falcon", "FalconForCausalLM"),
"Fairseq2LlamaForCausalLM": ("fairseq2_llama", "Fairseq2LlamaForCausalLM"),
"GemmaForCausalLM": ("gemma", "GemmaForCausalLM"),
"Gemma2ForCausalLM": ("gemma2", "Gemma2ForCausalLM"),
"GlmForCausalLM": ("glm", "GlmForCausalLM"),