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 11, 01:15 UTC
[CI Failure] Disable mosaicml/mpt-7b and databricks/dbrx-instruct tests (#31182)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Dec 22, 2025 at 18:40 UTC
6d518ffbaa04d3e930b320830542b6baf49aa61c
3 files changed
+9
-4
docs/serving/integrations/langchain.md
+1
-1
@@ -16,7 +16,7 @@ To run inference on a single or multiple GPUs, use `VLLM` class from `langchain`
16
from langchain_community.llms import VLLM
17
18
llm = VLLM(
19
- model="mosaicml/mpt-7b",
19
+ model="Qwen/Qwen3-4B",
20
trust_remote_code=True, # mandatory for hf models
21
max_new_tokens=128,
22
top_k=10,
tests/models/registry.py
+6
-2
@@ -215,7 +215,10 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
215
trust_remote_code=True,
216
),
217
"CwmForCausalLM": _HfExamplesInfo("facebook/cwm", min_transformers_version="4.58"),
218
- "DbrxForCausalLM": _HfExamplesInfo("databricks/dbrx-instruct"),
218
+ # FIXME: databricks/dbrx-instruct has been deleted
219
+ "DbrxForCausalLM": _HfExamplesInfo(
220
+ "databricks/dbrx-instruct", is_available_online=False
221
+ ),
222
"DeciLMForCausalLM": _HfExamplesInfo(
223
"nvidia/Llama-3_3-Nemotron-Super-49B-v1",
224
trust_remote_code=True,
@@ -366,7 +369,8 @@ _TEXT_GENERATION_EXAMPLE_MODELS = {
369
{"tiny": "TitanML/tiny-mixtral"},
370
),
371
"MptForCausalLM": _HfExamplesInfo("mpt", is_available_online=False),
369
- "MPTForCausalLM": _HfExamplesInfo("mosaicml/mpt-7b"),
372
+ # FIXME: mosaicml/mpt-7b has been deleted
373
+ "MPTForCausalLM": _HfExamplesInfo("mosaicml/mpt-7b", is_available_online=False),
374
"NemotronForCausalLM": _HfExamplesInfo("nvidia/Minitron-8B-Base"),
375
"NemotronHForCausalLM": _HfExamplesInfo(
376
"nvidia/Nemotron-H-8B-Base-8K", trust_remote_code=True
tests/tokenizers_/test_detokenize.py
+2
-1
@@ -38,7 +38,8 @@ TOKENIZERS = [
38
"EleutherAI/gpt-j-6b",
39
"EleutherAI/pythia-70m",
40
"bigscience/bloom-560m",
41
- "mosaicml/mpt-7b",
41
+ # FIXME: mosaicml/mpt-7b has been deleted
42
+ # "mosaicml/mpt-7b",
43
"tiiuae/falcon-7b",
44
"meta-llama/Llama-3.2-1B-Instruct",
45
"codellama/CodeLlama-7b-hf",