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, 23:30 UTC
[Docs] Update oneshot imports (#28188)
Signed-off-by: UranusSeven <109661872+UranusSeven@users.noreply.github.com>
Uranus committed
Nov 19, 2025 at 13:30 UTC
6a25ea5f0ea193e35b5a83cb0285c48964bc9eb1
4 files changed
+4
-4
docs/features/quantization/fp8.md
+1
-1
@@ -60,7 +60,7 @@ Since simple RTN does not require data for weight quantization and the activatio
60
??? code
61
62
```python
63
- from llmcompressor.transformers import oneshot
63
+ from llmcompressor import oneshot
64
from llmcompressor.modifiers.quantization import QuantizationModifier
65
66
# Configure the simple PTQ quantization
docs/features/quantization/int4.md
+1
-1
@@ -80,7 +80,7 @@ Now, apply the quantization algorithms:
80
??? code
81
82
```python
83
- from llmcompressor.transformers import oneshot
83
+ from llmcompressor import oneshot
84
from llmcompressor.modifiers.quantization import GPTQModifier
85
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
86
docs/features/quantization/int8.md
+1
-1
@@ -87,7 +87,7 @@ Now, apply the quantization algorithms:
87
??? code
88
89
```python
90
- from llmcompressor.transformers import oneshot
90
+ from llmcompressor import oneshot
91
from llmcompressor.modifiers.quantization import GPTQModifier
92
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
93
docs/features/quantization/quantized_kvcache.md
+1
-1
@@ -78,7 +78,7 @@ Here's a complete example using `meta-llama/Llama-3.1-8B-Instruct` (most models
78
```python
79
from datasets import load_dataset
80
from transformers import AutoModelForCausalLM, AutoTokenizer
81
- from llmcompressor.transformers import oneshot
81
+ from llmcompressor import oneshot
82
83
# Select model and load it
84
MODEL_ID = "meta-llama/Llama-3.1-8B-Instruct"