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 12, 19:45 UTC
Update model references for OLMo3 (#29099)
Signed-off-by: mgoin <mgoin64@gmail.com> Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Michael Goin committed
Nov 20, 2025 at 20:16 UTC
87cbbdff639f96766d4f6604cc970394c550dc5b
2 files changed
+2
-2
docs/models/supported_models.md
+1
-1
@@ -424,7 +424,7 @@ th {
424
| `NemotronHForCausalLM` | Nemotron-H | `nvidia/Nemotron-H-8B-Base-8K`, `nvidia/Nemotron-H-47B-Base-8K`, `nvidia/Nemotron-H-56B-Base-8K`, etc. | ✅︎ | ✅︎ |
425
| `OLMoForCausalLM` | OLMo | `allenai/OLMo-1B-hf`, `allenai/OLMo-7B-hf`, etc. | ✅︎ | ✅︎ |
426
| `OLMo2ForCausalLM` | OLMo2 | `allenai/OLMo-2-0425-1B`, etc. | ✅︎ | ✅︎ |
427
-| `OLMo3ForCausalLM` | OLMo3 | TBA | ✅︎ | ✅︎ |
427
+| `OLMo3ForCausalLM` | OLMo3 | `allenai/Olmo-3-7B-Instruct`, `allenai/Olmo-3-32B-Think`, etc. | ✅︎ | ✅︎ |
428
| `OLMoEForCausalLM` | OLMoE | `allenai/OLMoE-1B-7B-0924`, `allenai/OLMoE-1B-7B-0924-Instruct`, etc. | | ✅︎ |
429
| `OPTForCausalLM` | OPT, OPT-IML | `facebook/opt-66b`, `facebook/opt-iml-max-30b`, etc. | ✅︎ | ✅︎ |
430
| `OrionForCausalLM` | Orion | `OrionStarAI/Orion-14B-Base`, `OrionStarAI/Orion-14B-Chat`, etc. | | ✅︎ |
tests/models/registry.py
+1
-1
@@ -370,7 +370,7 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
370
),
371
"OlmoForCausalLM": _HfExamplesInfo("allenai/OLMo-1B-hf"),
372
"Olmo2ForCausalLM": _HfExamplesInfo("allenai/OLMo-2-0425-1B"),
373
- "Olmo3ForCausalLM": _HfExamplesInfo("shanearora/2025-sep-a-base-model"),
373
+ "Olmo3ForCausalLM": _HfExamplesInfo("allenai/Olmo-3-7B-Instruct"),
374
"OlmoeForCausalLM": _HfExamplesInfo("allenai/OLMoE-1B-7B-0924-Instruct"),
375
"OpenPanguMTPModel": _HfExamplesInfo(
376
"FreedomIntelligence/openPangu-Ultra-MoE-718B-V1.1",