A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 04:30 UTC
[CI] Fix broken CI (#11543)
Robert Shaw committed
Dec 26, 2024 at 21:49 UTC
46d4359450cd194ab2a4f2fdc370ff4b33a188e2
1 file changed
+2
tests/models/registry.py
+2
@@ -61,6 +61,8 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
61
"DeepseekForCausalLM": _HfExamplesInfo("deepseek-ai/deepseek-llm-7b-chat"),
62
"DeepseekV2ForCausalLM": _HfExamplesInfo("deepseek-ai/DeepSeek-V2-Lite-Chat", # noqa: E501
63
trust_remote_code=True),
64
+ "DeepseekV3ForCausalLM": _HfExamplesInfo("deepseek-ai/DeepSeek-V3", # noqa: E501
65
+ trust_remote_code=True),
66
"ExaoneForCausalLM": _HfExamplesInfo("LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct"), # noqa: E501
67
"FalconForCausalLM": _HfExamplesInfo("tiiuae/falcon-7b"),
68
"GemmaForCausalLM": _HfExamplesInfo("google/gemma-2b"),