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 14, 05:30 UTC
[Bugfix] Fix Apertus HF repo name (#24447)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Cyrus Leung committed
Sep 9, 2025 at 12:40 UTC
948dd3443bc6b8ffb76cbdddf3f4c5ae0b6637fa
3 files changed
+3
-2
docs/models/supported_models.md
+1
@@ -322,6 +322,7 @@ th {
322
323
| Architecture | Models | Example HF Models | [LoRA](../features/lora.md) | [PP](../serving/parallelism_scaling.md) | [V1](gh-issue:8779) |
324
|--------------|--------|-------------------|----------------------|---------------------------|---------------------|
325
+| `ApertusForCausalLM` | Apertus | `swiss-ai/Apertus-8B-2509`, `swiss-ai/Apertus-70B-Instruct-2509`, etc. | ✅︎ | ✅︎ | ✅︎ |
326
| `AquilaForCausalLM` | Aquila, Aquila2 | `BAAI/Aquila-7B`, `BAAI/AquilaChat-7B`, etc. | ✅︎ | ✅︎ | ✅︎ |
327
| `ArceeForCausalLM` | Arcee (AFM) | `arcee-ai/AFM-4.5B-Base`, etc. | ✅︎ | ✅︎ | ✅︎ |
328
| `ArcticForCausalLM` | Arctic | `Snowflake/snowflake-arctic-base`, `Snowflake/snowflake-arctic-instruct`, etc. | | ✅︎ | ✅︎ |
tests/models/language/generation/test_common.py
+1
-1
@@ -93,7 +93,7 @@ AITER_MODEL_LIST = [
93
"allenai/OLMoE-1B-7B-0924-Instruct",
94
marks=[pytest.mark.cpu_model],
95
),
96
- pytest.param("swiss-ai/Apertus-8B"), # apertus
96
+ pytest.param("swiss-ai/Apertus-8B-2509"), # apertus
97
])
98
@pytest.mark.parametrize("max_tokens", [32])
99
@pytest.mark.parametrize("num_logprobs", [5])
tests/models/registry.py
+1
-1
@@ -158,7 +158,7 @@ class _HfExamplesInfo:
158
# yapf: disable
159
_TEXT_GENERATION_EXAMPLE_MODELS = {
160
# [Decoder-only]
161
- "ApertusForCausalLM": _HfExamplesInfo("swiss-ai/Apertus-8B",
161
+ "ApertusForCausalLM": _HfExamplesInfo("swiss-ai/Apertus-8B-2509",
162
min_transformers_version="4.56.0",
163
trust_remote_code=True),
164
"AquilaModel": _HfExamplesInfo("BAAI/AquilaChat-7B",