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, 12:15 UTC
[Doc] Fix QWen3MOE info (#17381)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Jee Jee Li committed
Apr 29, 2025 at 20:38 UTC
890f104cdfe559136249872955e7234ea1bd298d
2 files changed
+4
-12
docs/source/models/supported_models.md
+2
-2
@@ -542,8 +542,8 @@ See [this page](#generative-models) for more information on how to use generativ
542
* ✅︎
543
- * `Qwen3MoeForCausalLM`
544
* Qwen3MoE
545
- * `Qwen/Qwen3-MoE-15B-A2B`, etc.
546
- * ✅︎
545
+ * `Qwen/Qwen3-30B-A3B`, etc.
546
+ *
547
* ✅︎
548
- * `StableLmForCausalLM`
549
* StableLM
tests/models/registry.py
+2
-10
@@ -217,16 +217,8 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
217
"Qwen2ForCausalLM": _HfExamplesInfo("Qwen/Qwen2-0.5B-Instruct",
218
extras={"2.5": "Qwen/Qwen2.5-0.5B-Instruct"}), # noqa: E501
219
"Qwen2MoeForCausalLM": _HfExamplesInfo("Qwen/Qwen1.5-MoE-A2.7B-Chat"),
220
- "Qwen3ForCausalLM": _HfExamplesInfo(
221
- "Qwen/Qwen3-8B",
222
- is_available_online=False,
223
- min_transformers_version="4.51"
224
- ),
225
- "Qwen3MoeForCausalLM": _HfExamplesInfo(
226
- "Qwen/Qwen3-MoE-15B-A2B",
227
- is_available_online=False,
228
- min_transformers_version="4.51"
229
- ),
220
+ "Qwen3ForCausalLM": _HfExamplesInfo("Qwen/Qwen3-8B"),
221
+ "Qwen3MoeForCausalLM": _HfExamplesInfo("Qwen/Qwen3-30B-A3B"),
222
"RWForCausalLM": _HfExamplesInfo("tiiuae/falcon-40b",
223
is_available_online=False),
224
"StableLMEpochForCausalLM": _HfExamplesInfo("stabilityai/stablelm-zephyr-3b", # noqa: E501