Merge branch 'main' into kylesayrs/shared-pipelines

Author: kylesayrs

README.md

@@ -12,6 +12,14 @@
    <img alt="LLM Compressor Flow" src="https://github.com/user-attachments/assets/adf07594-6487-48ae-af62-d9555046d51b" width="80%" />
 </p>
 
+## 🚀 What's New!
+
+Big updates have landed in LLM Compressor! Check out these exciting new features:
+
+* **Axolotl Sparse Finetuning Integration:** Easily finetune sparse LLMs through our seamless integration with Axolotl. [Learn more here](https://docs.axolotl.ai/docs/custom_integrations.html#llmcompressor).
+* **AutoAWQ Integration:** Perform low-bit weight-only quantization efficiently using AutoAWQ, now part of LLM Compressor. *Note: This integration should be considered experimental for now. Enhanced support, including for MoE models and improved handling of larger models via layer sequential pipelining, is planned for upcoming releases.* [See the details](https://github.com/vllm-project/llm-compressor/pull/1177).
+* **Day 0 Llama 4 Support:** Meta utilized LLM Compressor to create the [FP8-quantized Llama-4-Maverick-17B-128E](https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8), optimized for vLLM inference using [compressed-tensors](https://github.com/neuralmagic/compressed-tensors) format.
+
 ### Supported Formats
 * Activation Quantization: W8A8 (int8 and fp8)
 * Mixed Precision: W4A16, W8A16

examples/multimodal_vision/gemma3_example.py

@@ -0,0 +1,75 @@
+import requests
+import torch
+from PIL import Image
+from transformers import AutoProcessor
+
+from llmcompressor import oneshot
+from llmcompressor.modifiers.quantization import GPTQModifier
+from llmcompressor.transformers.tracing import TraceableGemma3ForConditionalGeneration
+
+# Load model.
+model_id = "google/gemma-3-4b-it"
+model = TraceableGemma3ForConditionalGeneration.from_pretrained(
+    model_id, device_map="auto", torch_dtype="auto"
+)
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
+
+# Oneshot arguments
+DATASET_ID = "flickr30k"
+DATASET_SPLIT = {"calibration": "test[:512]"}
+NUM_CALIBRATION_SAMPLES = 512
+MAX_SEQUENCE_LENGTH = 2048
+
+
+# Define a oneshot data collator for multimodal inputs.
+def data_collator(batch):
+    assert len(batch) == 1
+    return {key: torch.tensor(value) for key, value in batch[0].items()}
+
+
+# Recipe
+recipe = [
+    GPTQModifier(
+        targets="Linear",
+        scheme="W4A16",
+        ignore=["re:*.lm_head", "re:vision_tower.*", "re:multi_modal_projector.*"],
+    ),
+]
+
+# Perform oneshot
+oneshot(
+    model=model,
+    tokenizer=model_id,
+    dataset=DATASET_ID,
+    splits=DATASET_SPLIT,
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+    trust_remote_code_model=True,
+    data_collator=data_collator,
+)
+
+# Confirm generations of the quantized model look sane.
+print("========== SAMPLE GENERATION ==============")
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "Please describe the animal in this image\n"},
+            {"type": "image"},
+        ],
+    },
+]
+prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
+image_url = "http://images.cocodataset.org/train2017/000000231895.jpg"
+raw_image = Image.open(requests.get(image_url, stream=True).raw)
+
+inputs = processor(images=raw_image, text=prompt, return_tensors="pt").to("cuda")
+output = model.generate(**inputs, max_new_tokens=100)
+print(processor.decode(output[0], skip_special_tokens=True))
+print("==========================================")
+
+# Save to disk compressed.
+SAVE_DIR = model_id.split("/")[1] + "-W4A16-G128"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+processor.save_pretrained(SAVE_DIR)

src/llmcompressor/transformers/tracing/__init__.py

@@ -1,3 +1,6 @@
+from .gemma3 import (
+    Gemma3ForConditionalGeneration as TraceableGemma3ForConditionalGeneration,
+)
 from .llava import (
     LlavaForConditionalGeneration as TraceableLlavaForConditionalGeneration,
 )
@@ -11,12 +14,13 @@
     Idefics3ForConditionalGeneration as TraceableIdefics3ForConditionalGeneration,
 )
 from .qwen2_5_vl import (
-    Qwen2_5_VLForConditionalGeneration as TraceableQwen2_5_VLForConditionalGeneration
+    Qwen2_5_VLForConditionalGeneration as TraceableQwen2_5_VLForConditionalGeneration,
 )
 from .debug import get_model_class
 
 __all__ = [
     "get_model_class",
+    "TraceableGemma3ForConditionalGeneration",
     "TraceableLlavaForConditionalGeneration",
     "TraceableMllamaForConditionalGeneration",
     "TraceableQwen2VLForConditionalGeneration",