Mistral Small 24B Instruct 2501 Quantized.w8a8

podman run --rm -it --device nvidia.com/gpu=all -p 8000:8000 \
 --ipc=host \
--env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
--env "HF_HUB_OFFLINE=0" -v ~/.cache/vllm:/home/vllm/.cache \
--name=vllm \
registry.access.redhat.com/rhaiis/rh-vllm-cuda \
vllm serve \
--tensor-parallel-size 8 \
--max-model-len 32768  \
--enforce-eager --model RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8

See Red Hat AI Inference Server documentation for more details.

# Download model from Red Hat Registry via docker
# Note: This downloads the model to ~/.cache/instructlab/models unless --model-dir is specified.
ilab model download --repository docker://registry.redhat.io/rhelai1/mistral-small-24b-instruct-2501-quantized-w8a8:1.5

# Serve model via ilab
ilab model serve --model-path ~/.cache/instructlab/models/mistral-small-24b-instruct-2501-quantized-w8a8

# Chat with model
ilab model chat --model ~/.cache/instructlab/models/mistral-small-24b-instruct-2501-quantized-w8a8

See Red Hat Enterprise Linux AI documentation for more details.

# Setting up vllm server with ServingRuntime
# Save as: vllm-servingruntime.yaml
apiVersion: serving.kserve.io/v1alpha1
kind: ServingRuntime
metadata:
 name: vllm-cuda-runtime # OPTIONAL CHANGE: set a unique name
 annotations:
   openshift.io/display-name: vLLM NVIDIA GPU ServingRuntime for KServe
   opendatahub.io/recommended-accelerators: '["nvidia.com/gpu"]'
 labels:
   opendatahub.io/dashboard: 'true'
spec:
 annotations:
   prometheus.io/port: '8080'
   prometheus.io/path: '/metrics'
 multiModel: false
 supportedModelFormats:
   - autoSelect: true
     name: vLLM
 containers:
   - name: kserve-container
     image: quay.io/modh/vllm:rhoai-2.20-cuda # CHANGE if needed. If AMD: quay.io/modh/vllm:rhoai-2.20-rocm
     command:
       - python
       - -m
       - vllm.entrypoints.openai.api_server
     args:
       - "--port=8080"
       - "--model=/mnt/models"
       - "--served-model-name={{.Name}}"
     env:
       - name: HF_HOME
         value: /tmp/hf_home
     ports:
       - containerPort: 8080
         protocol: TCP

# Attach model to vllm server. This is an NVIDIA template
# Save as: inferenceservice.yaml
apiVersion: serving.kserve.io/v1beta1
kind: InferenceService
metadata:
  annotations:
    openshift.io/display-name: mistral-small-24b-instruct-2501-quantized-w8a8 # OPTIONAL CHANGE
    serving.kserve.io/deploymentMode: RawDeployment
  name: mistral-small-24b-instruct-2501-quantized-w8a8         # specify model name. This value will be used to invoke the model in the payload
  labels:
    opendatahub.io/dashboard: 'true'
spec:
  predictor:
    maxReplicas: 1
    minReplicas: 1
    model:
      modelFormat:
        name: vLLM
      name: ''
      resources:
        limits:
          cpu: '2'			# this is model specific
          memory: 8Gi		# this is model specific
          nvidia.com/gpu: '1'	# this is accelerator specific
        requests:			# same comment for this block
          cpu: '1'
          memory: 4Gi
          nvidia.com/gpu: '1'
      runtime: vllm-cuda-runtime	# must match the ServingRuntime name above
      storageUri: oci://registry.redhat.io/rhelai1/modelcar-mistral-small-24b-instruct-2501-quantized-w8a8:1.5
    tolerations:
    - effect: NoSchedule
      key: nvidia.com/gpu
      operator: Exists

# make sure first to be in the project where you want to deploy the model
# oc project <project-name>

# apply both resources to run model

# Apply the ServingRuntime
oc apply -f vllm-servingruntime.yaml

# Apply the InferenceService
oc apply -f qwen-inferenceservice.yaml

# Replace <inference-service-name> and <cluster-ingress-domain> below:
# - Run `oc get inferenceservice` to find your URL if unsure.

# Call the server using curl:
curl https://<inference-service-name>-predictor-default.<domain>/v1/chat/completions
        -H "Content-Type: application/json" \
        -d '{
    "model": "mistral-small-24b-instruct-2501-quantized-w8a8",
    "stream": true,
    "stream_options": {
        "include_usage": true
    },
    "max_tokens": 1,
    "messages": [
        {
            "role": "user",
            "content": "How can a bee fly when its wings are so small?"
        }
    ]
}'

See Red Hat Openshift AI documentation for more details.

from transformers import AutoTokenizer, AutoModelForCausalLM
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
from llmcompressor.transformers import oneshot
from datasets import load_dataset

# Load model
model_stub = "mistralai/Mistral-Small-24B-Instruct-2501"
model_name = model_stub.split("/")[-1]

num_samples = 1024
max_seq_len = 8192

tokenizer = AutoTokenizer.from_pretrained(model_stub)

model = AutoModelForCausalLM.from_pretrained(
    model_stub,
    device_map="auto",
    torch_dtype="auto",
)

# Data processing
def preprocess_text(example):
    text = tokenizer.apply_chat_template(example["messages"], tokenize=False, add_generation_prompt=False)
    return tokenizer(text, padding=False, max_length=max_seq_len, truncation=True)

ds = load_dataset("neuralmagic/calibration", name="LLM", split="train").select(range(num_samples))
ds = ds.map(preprocess_text, remove_columns=ds.column_names)

# Configure the quantization algorithm and scheme
recipe = [
    SmoothQuantModifier(
      smoothing_strength=0.9,
      mappings=[
          [["re:.*q_proj", "re:.*k_proj", "re:.*v_proj"], "re:.*input_layernorm"],
          [["re:.*gate_proj", "re:.*up_proj"], "re:.*post_attention_layernorm"],
          [["re:.*down_proj"], "re:.*up_proj"],
      ],
    ),
    GPTQModifier(
        ignore=["lm_head"],
        sequential_targets=["MistralDecoderLayer"],
        dampening_frac=0.1,
        targets="Linear",
        scheme="W8A8",
    ),
]

# Apply quantization
oneshot(
    model=model,
    dataset=ds,
    recipe=recipe,
    max_seq_length=max_seq_len,
    num_calibration_samples=num_samples
)

# Save to disk in compressed-tensors format
save_path = model_name + "-quantized.w8a8"
model.save_pretrained(save_path)
processor.save_pretrained(save_path)
print(f"Model and tokenizer saved to: {save_path}")