Document OrbitQuant 0.4.0 on-the-fly conversion

README.md

@@ -32,7 +32,7 @@ OrbitQuant paper itself leaves text encoders in BF16.
 ## Install
 
 ```bash
-pip install "orbitquant[kernels]>=0.3.1" "diffusers>=0.39" "transformers>=5.13" accelerate
+pip install "orbitquant[hf,kernels]>=0.4.0"
 ```
 
 OrbitQuant uses packed low-bit inference by default. CUDA first uses an importable
@@ -71,6 +71,40 @@ image = pipe(
 image.save("orbitquant.png")
 ```
 
+## Convert the source checkpoint on load
+
+To create a fresh transformer-only OrbitQuant pipeline directly from the source
+safetensors checkpoint, use the normal Diffusers loader. This row-streams source
+weights into packed tensors instead of keeping the complete BF16 transformer and
+the quantized transformer resident together:
+
+```python
+import torch
+import orbitquant
+from diffusers import DiffusionPipeline
+from orbitquant import (
+    OrbitQuantConfig,
+    build_diffusers_pipeline_quantization_config,
+)
+
+qconfig = build_diffusers_pipeline_quantization_config(
+    OrbitQuantConfig(target_policy="auto"),
+    components="transformer",
+)
+pipe = DiffusionPipeline.from_pretrained(
+    "black-forest-labs/FLUX.2-klein-9B",
+    quantization_config=qconfig,
+    torch_dtype=torch.bfloat16,
+)
+pipe.enable_model_cpu_offload()
+```
+
+Use `pipe.enable_sequential_cpu_offload()` instead for sequential offload. The
+published artifact also quantizes its text encoder for the SDNQ comparison;
+on-the-fly conversion keeps text encoders in source precision unless they are
+explicitly included in `components`. Guaranteed bounded-memory conversion
+requires a safetensors source checkpoint.
+
 ## Transformers Component
 
 The quantized Qwen3 component can also be loaded through Transformers:

SHA256SUMS

@@ -1,5 +1,5 @@
 468d9f4332c0c895e9132c035982a40a12750092603a2e910913cb49aa887d3b  ./LICENSE.md
-7d4f666483bfadb61d7a7cbb504441b6945f3b03744770f1382b42b4512882e5  ./README.md
+f130b8f439a4090defa68feb0ecb17e5616b902b259a4281539a4a0ddcd18bee  ./README.md
 02f199e9e833501e8ee57418016ca3514376a90a6f952c46e2542c6d1ec3ff27  ./assets/image_generation_comparison_matrix.webp
 8155fb3d937b8dca2113f5bd16dbba847104ed3420c34bdedc551b3e6f792120  ./benchmark/build.json
 1eccd6b514c82c9bb71d7705ca92761f1b54e9daae881d010bad4ba0251254be  ./benchmark/summary.json