biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[doc] Fold long code blocks to improve readability (#19926)

Browse Source 
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
This commit is contained in:
Reid
2025-06-23 13:24:23 +08:00
committed by GitHub
parent 493c275352
commit f17aec0d63
50 changed files with 3455 additions and 3180 deletions
Download Patch File Download Diff File Expand all files Collapse all files

212
docs/features/quantization/quark.md
View File

@@ -42,20 +42,22 @@ The Quark quantization process can be listed for 5 steps as below:
Quark uses [Transformers](https://huggingface.co/docs/transformers/en/index)
to fetch model and tokenizer.
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
??? Code
MODEL_ID = "meta-llama/Llama-2-70b-chat-hf"
MAX_SEQ_LEN = 512
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID, device_map="auto", torch_dtype="auto",
)
model.eval()
MODEL_ID = "meta-llama/Llama-2-70b-chat-hf"
MAX_SEQ_LEN = 512
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, model_max_length=MAX_SEQ_LEN)
tokenizer.pad_token = tokenizer.eos_token
```
model = AutoModelForCausalLM.from_pretrained(
MODEL_ID, device_map="auto", torch_dtype="auto",
)
model.eval()
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, model_max_length=MAX_SEQ_LEN)
tokenizer.pad_token = tokenizer.eos_token
```
### 2. Prepare the Calibration Dataloader
@@ -63,22 +65,24 @@ Quark uses the [PyTorch Dataloader](https://pytorch.org/tutorials/beginner/basic
to load calibration data. For more details about how to use calibration datasets efficiently, please refer
to [Adding Calibration Datasets](https://quark.docs.amd.com/latest/pytorch/calibration_datasets.html).
```python
from datasets import load_dataset
from torch.utils.data import DataLoader
??? Code
BATCH_SIZE = 1
NUM_CALIBRATION_DATA = 512
```python
from datasets import load_dataset
from torch.utils.data import DataLoader
# Load the dataset and get calibration data.
dataset = load_dataset("mit-han-lab/pile-val-backup", split="validation")
text_data = dataset["text"][:NUM_CALIBRATION_DATA]
BATCH_SIZE = 1
NUM_CALIBRATION_DATA = 512
tokenized_outputs = tokenizer(text_data, return_tensors="pt",
padding=True, truncation=True, max_length=MAX_SEQ_LEN)
calib_dataloader = DataLoader(tokenized_outputs['input_ids'],
batch_size=BATCH_SIZE, drop_last=True)
```
# Load the dataset and get calibration data.
dataset = load_dataset("mit-han-lab/pile-val-backup", split="validation")
text_data = dataset["text"][:NUM_CALIBRATION_DATA]
tokenized_outputs = tokenizer(text_data, return_tensors="pt",
padding=True, truncation=True, max_length=MAX_SEQ_LEN)
calib_dataloader = DataLoader(tokenized_outputs['input_ids'],
batch_size=BATCH_SIZE, drop_last=True)
```
### 3. Set the Quantization Configuration
@@ -94,42 +98,44 @@ kv-cache and the quantization algorithm is AutoSmoothQuant.
AutoSmoothQuant config file for Llama is
`examples/torch/language_modeling/llm_ptq/models/llama/autosmoothquant_config.json`.
```python
from quark.torch.quantization import (Config, QuantizationConfig,
FP8E4M3PerTensorSpec,
load_quant_algo_config_from_file)
??? Code
# Define fp8/per-tensor/static spec.
FP8_PER_TENSOR_SPEC = FP8E4M3PerTensorSpec(observer_method="min_max",
is_dynamic=False).to_quantization_spec()
```python
from quark.torch.quantization import (Config, QuantizationConfig,
FP8E4M3PerTensorSpec,
load_quant_algo_config_from_file)
# Define global quantization config, input tensors and weight apply FP8_PER_TENSOR_SPEC.
global_quant_config = QuantizationConfig(input_tensors=FP8_PER_TENSOR_SPEC,
weight=FP8_PER_TENSOR_SPEC)
# Define fp8/per-tensor/static spec.
FP8_PER_TENSOR_SPEC = FP8E4M3PerTensorSpec(observer_method="min_max",
is_dynamic=False).to_quantization_spec()
# Define quantization config for kv-cache layers, output tensors apply FP8_PER_TENSOR_SPEC.
KV_CACHE_SPEC = FP8_PER_TENSOR_SPEC
kv_cache_layer_names_for_llama = ["*k_proj", "*v_proj"]
kv_cache_quant_config = {name :
QuantizationConfig(input_tensors=global_quant_config.input_tensors,
weight=global_quant_config.weight,
output_tensors=KV_CACHE_SPEC)
for name in kv_cache_layer_names_for_llama}
layer_quant_config = kv_cache_quant_config.copy()
# Define global quantization config, input tensors and weight apply FP8_PER_TENSOR_SPEC.
global_quant_config = QuantizationConfig(input_tensors=FP8_PER_TENSOR_SPEC,
weight=FP8_PER_TENSOR_SPEC)
# Define algorithm config by config file.
LLAMA_AUTOSMOOTHQUANT_CONFIG_FILE =
'examples/torch/language_modeling/llm_ptq/models/llama/autosmoothquant_config.json'
algo_config = load_quant_algo_config_from_file(LLAMA_AUTOSMOOTHQUANT_CONFIG_FILE)
# Define quantization config for kv-cache layers, output tensors apply FP8_PER_TENSOR_SPEC.
KV_CACHE_SPEC = FP8_PER_TENSOR_SPEC
kv_cache_layer_names_for_llama = ["*k_proj", "*v_proj"]
kv_cache_quant_config = {name :
QuantizationConfig(input_tensors=global_quant_config.input_tensors,
weight=global_quant_config.weight,
output_tensors=KV_CACHE_SPEC)
for name in kv_cache_layer_names_for_llama}
layer_quant_config = kv_cache_quant_config.copy()
EXCLUDE_LAYERS = ["lm_head"]
quant_config = Config(
global_quant_config=global_quant_config,
layer_quant_config=layer_quant_config,
kv_cache_quant_config=kv_cache_quant_config,
exclude=EXCLUDE_LAYERS,
algo_config=algo_config)
```
# Define algorithm config by config file.
LLAMA_AUTOSMOOTHQUANT_CONFIG_FILE =
'examples/torch/language_modeling/llm_ptq/models/llama/autosmoothquant_config.json'
algo_config = load_quant_algo_config_from_file(LLAMA_AUTOSMOOTHQUANT_CONFIG_FILE)
EXCLUDE_LAYERS = ["lm_head"]
quant_config = Config(
global_quant_config=global_quant_config,
layer_quant_config=layer_quant_config,
kv_cache_quant_config=kv_cache_quant_config,
exclude=EXCLUDE_LAYERS,
algo_config=algo_config)
```
### 4. Quantize the Model and Export
@@ -139,63 +145,67 @@ HuggingFace `safetensors`, you can refer to
[HuggingFace format exporting](https://quark.docs.amd.com/latest/pytorch/export/quark_export_hf.html)
for more exporting format details.
```python
import torch
from quark.torch import ModelQuantizer, ModelExporter
from quark.torch.export import ExporterConfig, JsonExporterConfig
??? Code
# Apply quantization.
quantizer = ModelQuantizer(quant_config)
quant_model = quantizer.quantize_model(model, calib_dataloader)
```python
import torch
from quark.torch import ModelQuantizer, ModelExporter
from quark.torch.export import ExporterConfig, JsonExporterConfig
# Freeze quantized model to export.
freezed_model = quantizer.freeze(model)
# Apply quantization.
quantizer = ModelQuantizer(quant_config)
quant_model = quantizer.quantize_model(model, calib_dataloader)
# Define export config.
LLAMA_KV_CACHE_GROUP = ["*k_proj", "*v_proj"]
export_config = ExporterConfig(json_export_config=JsonExporterConfig())
export_config.json_export_config.kv_cache_group = LLAMA_KV_CACHE_GROUP
# Freeze quantized model to export.
freezed_model = quantizer.freeze(model)
# Model: Llama-2-70b-chat-hf-w-fp8-a-fp8-kvcache-fp8-pertensor-autosmoothquant
EXPORT_DIR = MODEL_ID.split("/")[1] + "-w-fp8-a-fp8-kvcache-fp8-pertensor-autosmoothquant"
exporter = ModelExporter(config=export_config, export_dir=EXPORT_DIR)
with torch.no_grad():
exporter.export_safetensors_model(freezed_model,
quant_config=quant_config, tokenizer=tokenizer)
```
# Define export config.
LLAMA_KV_CACHE_GROUP = ["*k_proj", "*v_proj"]
export_config = ExporterConfig(json_export_config=JsonExporterConfig())
export_config.json_export_config.kv_cache_group = LLAMA_KV_CACHE_GROUP
# Model: Llama-2-70b-chat-hf-w-fp8-a-fp8-kvcache-fp8-pertensor-autosmoothquant
EXPORT_DIR = MODEL_ID.split("/")[1] + "-w-fp8-a-fp8-kvcache-fp8-pertensor-autosmoothquant"
exporter = ModelExporter(config=export_config, export_dir=EXPORT_DIR)
with torch.no_grad():
exporter.export_safetensors_model(freezed_model,
quant_config=quant_config, tokenizer=tokenizer)
```
### 5. Evaluation in vLLM
Now, you can load and run the Quark quantized model directly through the LLM entrypoint:
```python
from vllm import LLM, SamplingParams
??? Code
# Sample prompts.
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
```python
from vllm import LLM, SamplingParams
# Create an LLM.
llm = LLM(model="Llama-2-70b-chat-hf-w-fp8-a-fp8-kvcache-fp8-pertensor-autosmoothquant",
kv_cache_dtype='fp8',quantization='quark')
# Generate texts from the prompts. The output is a list of RequestOutput objects
# that contain the prompt, generated text, and other information.
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
print("\nGenerated Outputs:\n" + "-" * 60)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}")
print(f"Output: {generated_text!r}")
print("-" * 60)
```
# Sample prompts.
prompts = [
"Hello, my name is",
"The president of the United States is",
"The capital of France is",
"The future of AI is",
]
# Create a sampling params object.
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
# Create an LLM.
llm = LLM(model="Llama-2-70b-chat-hf-w-fp8-a-fp8-kvcache-fp8-pertensor-autosmoothquant",
kv_cache_dtype='fp8',quantization='quark')
# Generate texts from the prompts. The output is a list of RequestOutput objects
# that contain the prompt, generated text, and other information.
outputs = llm.generate(prompts, sampling_params)
# Print the outputs.
print("\nGenerated Outputs:\n" + "-" * 60)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}")
print(f"Output: {generated_text!r}")
print("-" * 60)
```
Or, you can use `lm_eval` to evaluate accuracy: