Small changes for docs build

Signed-off-by: Aidan Reilly <[email protected]>

Author: aireilly

.gitignore

@@ -93,9 +93,6 @@ instance/
 # Scrapy stuff:
 .scrapy
 
-# Sphinx documentation
-docs/_build/
-
 # PyBuilder
 target/
 
@@ -129,6 +126,7 @@ venv.bak/
 
 # mkdocs documentation
 /site
+docs/.cache/
 
 # mypy
 .mypy_cache/

docs/Makefile

@@ -0,0 +1,26 @@
+# Minimal mkdocs makefile
+
+PYTHON      := python3
+MKDOCS_CMD  := mkdocs
+MKDOCS_CONF := ../mkdocs.yml
+
+.PHONY: help install serve build clean
+
+help:
+	@echo "Available targets:"
+	@echo "  install  Install dependencies globally"
+	@echo "  serve    Serve docs locally"
+	@echo "  build    Build static site"
+	@echo "  clean    Remove build artifacts"
+
+install:
+	pip install -e "../[dev]"
+
+serve:
+	$(MKDOCS_CMD) serve --livereload -f $(MKDOCS_CONF)
+
+build:
+	$(MKDOCS_CMD) build -f $(MKDOCS_CONF)
+
+clean:
+	rm -rf site/ .cache/ 

docs/README.md

@@ -0,0 +1,25 @@
+# Getting started with LLM Compressor docs
+
+```bash
+cd docs
+```
+
+- Install the dependencies:
+
+```bash
+make install
+```
+
+- Clean the previous build (optional but recommended):
+
+```bash
+make clean
+```
+
+- Serve the docs:
+
+```bash
+make serve
+```
+
+This will start a local server at http://localhost:8000. You can now open your browser and view the documentation.

docs/index.md

@@ -1,11 +1,19 @@
 # Home
 
-!!! info "New Feature: Axolotl Sparse Finetuning Integration"
-    Easily finetune sparse LLMs through our seamless integration with Axolotl.
-    [Learn more](https://docs.axolotl.ai/docs/custom_integrations.html#llmcompressor).
+!!! info "Llama4 Quantization Support"
+    Quantize a Llama4 model to [W4A16](examples/quantization_w4a16.md) or [NVFP4](examples/quantization_w4a16.md). The checkpoint produced can seamlessly run in vLLM.
 
-!!! info "New Feature: AutoAWQ Integration"
-    Perform low-bit weight-only quantization efficiently using AutoAWQ, now part of LLM Compressor. [Learn more](https://github.com/vllm-project/llm-compressor/pull/1177).
+!!! info "Large Model Support with Sequential Onloading"
+    As of llm-compressor>=0.6.0, you can now quantize very large language models on a single GPU. Models are broken into disjoint layers which are then onloaded to the GPU one layer at a time. For more information on sequential onloading, see [Big Modeling with Sequential Onloading](examples/big_models_with_sequential_onloading.md) as well as the [DeepSeek-R1 Example](examples/quantizing_moe.md).
+
+!!! info "Preliminary FP4 Quantization Support"
+    Quantize weights and activations to FP4 and seamlessly run the compressed model in vLLM. Model weights and activations are quantized following the NVFP4 [configuration](https://github.com/neuralmagic/compressed-tensors/blob/f5dbfc336b9c9c361b9fe7ae085d5cb0673e56eb/src/compressed_tensors/quantization/quant_scheme.py#L104). See examples of [weight-only quantization](examples/quantization_w4a16_fp4.md) and [fp4 activation support](examples/quantization_w4a4_fp4.md). Support is currently preliminary and additional support will be added for MoEs.
+
+!!! info "Updated AWQ Support"
+    Improved support for MoEs with better handling of larger models
+
+!!! info "Axolotl Sparse Finetuning Integration"
+    Seamlessly finetune sparse LLMs with our Axolotl integration. Learn how to create [fast sparse open-source models with Axolotl and LLM Compressor](https://developers.redhat.com/articles/2025/06/17/axolotl-meets-llm-compressor-fast-sparse-open). See also the [Axolotl integration docs](https://docs.axolotl.ai/docs/custom_integrations.html#llmcompressor).
 
 ## <div style="display: flex; align-items: center;"><img alt="LLM Compressor Logo" src="assets/llmcompressor-icon.png" width="40" style="vertical-align: middle; margin-right: 10px" /> LLM Compressor</div>