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 15, 11:00 UTC
[Misc] replace does not exist model (#18119)
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
rongfu.leng committed
May 14, 2025 at 17:13 UTC
82e7f9bb031a9aabb320db88503b6f948ded6e95
4 files changed
+4
-4
docs/source/models/supported_models.md
+1
-1
@@ -539,7 +539,7 @@ Specified using `--task generate`.
539
* ✅︎
540
- * `OLMo2ForCausalLM`
541
* OLMo2
542
- * `allenai/OLMo2-7B-1124`, etc.
542
+ * `allenai/OLMo-2-0425-1B`, etc.
543
*
544
* ✅︎
545
- * `OLMoEForCausalLM`
tests/distributed/test_pipeline_parallel.py
+1
-1
@@ -185,7 +185,7 @@ TEXT_GENERATION_MODELS = {
185
"mosaicml/mpt-7b": PPTestSettings.fast(),
186
"nvidia/Minitron-8B-Base": PPTestSettings.fast(),
187
"allenai/OLMo-1B-hf": PPTestSettings.fast(),
188
- "shanearora/OLMo-7B-1124-hf": PPTestSettings.fast(),
188
+ "allenai/OLMo-2-0425-1B": PPTestSettings.fast(),
189
"allenai/OLMoE-1B-7B-0924-Instruct": PPTestSettings.fast(),
190
"facebook/opt-iml-max-1.3b": PPTestSettings.fast(),
191
"OrionStarAI/Orion-14B-Chat": PPTestSettings.fast(),
tests/models/registry.py
+1
-1
@@ -205,7 +205,7 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
205
"MPTForCausalLM": _HfExamplesInfo("mosaicml/mpt-7b"),
206
"NemotronForCausalLM": _HfExamplesInfo("nvidia/Minitron-8B-Base"),
207
"OlmoForCausalLM": _HfExamplesInfo("allenai/OLMo-1B-hf"),
208
- "Olmo2ForCausalLM": _HfExamplesInfo("shanearora/OLMo-7B-1124-hf"),
208
+ "Olmo2ForCausalLM": _HfExamplesInfo("allenai/OLMo-2-0425-1B"),
209
"OlmoeForCausalLM": _HfExamplesInfo("allenai/OLMoE-1B-7B-0924-Instruct"),
210
"OPTForCausalLM": _HfExamplesInfo("facebook/opt-125m",
211
{"1b": "facebook/opt-iml-max-1.3b"}),
vllm/test_utils.py
+1
-1
@@ -110,7 +110,7 @@ MODELS_ON_S3 = [
110
"royokong/e5-v",
111
"sentence-transformers/all-roberta-large-v1",
112
"sentence-transformers/stsb-roberta-base-v2",
113
- "shanearora/OLMo-7B-1124-hf",
113
+ "allenai/OLMo-2-0425-1B",
114
"shuyuej/Llama-3.2-1B-Instruct-GPTQ",
115
"ssmits/Qwen2-7B-Instruct-embed-base",
116
"stabilityai/stablelm-3b-4e1t",