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

Inclusion of InternVLChatModel In PP_SUPPORTED_MODELS(Pipeline Parallelism) (#7860)

Browse Source
This commit is contained in:
manikandan.tm@zucisystems.com
2024-09-05 17:03:37 +05:30
committed by GitHub
parent 288a938872
commit 8685ba1a1e
6 changed files with 90 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
vllm/config.py
View File

@@ -35,18 +35,20 @@ _EMBEDDING_MODEL_MAX_NUM_BATCHED_TOKENS = 32768
_MULTIMODAL_MODEL_MAX_NUM_BATCHED_TOKENS = 4096
_PP_SUPPORTED_MODELS = [
"AquilaModel",
"AquilaForCausalLM",
"AquilaModel",
"DeepseekV2ForCausalLM",
"GPT2LMHeadModel",
"InternLM2ForCausalLM",
"InternLMForCausalLM",
"InternVLChatModel",
"JAISLMHeadModel",
"LlamaForCausalLM",
"LLaMAForCausalLM",
"MistralForCausalLM",
"Phi3ForCausalLM",
"GPT2LMHeadModel",
"MixtralForCausalLM",
"NemotronForCausalLM",
"Phi3ForCausalLM",
"Qwen2ForCausalLM",
"Qwen2MoeForCausalLM",
"QWenLMHeadModel",