Release v1.0.1 with persistent Docker cache setup

BENCHMARKS.md

@@ -90,6 +90,6 @@ other generation services, then run:
 
 [Every measured timing](benchmark-data/raw-timings.csv) and
 [settings, memory, versions and quality](benchmark-data/results.json) are included.
-The [article and evidence bundle](https://github.com/Eliovp-BV/paiton-vllm-plugin/releases/tag/paiton-flux2-klein-gfx1201-v1.0.0)
+The [article and evidence bundle](https://github.com/Eliovp-BV/paiton-vllm-plugin/releases/tag/paiton-flux2-klein-gfx1201-v1.0.1)
 provides charts, full-resolution quality pairs, example media, startup details
 and the complete evidence archive.

README.md

@@ -20,7 +20,7 @@ tags:
 
 Generate photographs, product concepts and illustrations locally with a ready-to-run ComfyUI workflow. The qualified Paiton pipeline averages **1.054 seconds per 1024 × 1024 image** and uses just **12.9 GiB peak Torch allocation** on one AMD Radeon AI PRO R9700.
 
-**Release:** v1.0.0 · **GPU:** R9700, `gfx1201`, 32 GB · **Steps:** 4 · **Batch:** 1 · **Text-to-image**
+**Release:** v1.0.1 · **GPU:** R9700, `gfx1201`, 32 GB · **Steps:** 4 · **Batch:** 1 · **Text-to-image**
 
 This repository contains compiled runtime artifacts, manifests, licenses and example media. Model weights download separately from the original checkpoint publisher and remain in your local cache. The containers already include these artifacts, so no separate `.so` download is needed to start. The private Paiton compiler is not included or required.
 
@@ -29,18 +29,20 @@ This repository contains compiled runtime artifacts, manifests, licenses and exa
 You need Linux x86-64, Docker Engine with the Compose plugin, and working AMD GPU device access through `/dev/kfd` and `/dev/dri`.
 
 ```bash
-git clone --depth 1 --branch paiton-flux2-klein-gfx1201-v1.0.0 https://github.com/Eliovp-BV/paiton-vllm-plugin.git && cd paiton-vllm-plugin && ./models/FLUX.2-klein/launch.sh
+git clone --depth 1 --branch paiton-flux2-klein-gfx1201-v1.0.1 https://github.com/Eliovp-BV/paiton-vllm-plugin.git && cd paiton-vllm-plugin && ./models/FLUX.2-klein/launch.sh
 ```
 
 Open [ComfyUI on localhost](http://127.0.0.1:8188/?paiton=1). The first visit opens the included workflow. Enter a prompt, choose **Paiton** or **Stock (Diffusers)**, and click **Run**. Preview and Save Image work normally. Images go to `paiton-images/`.
 
 ![ComfyUI with the included Paiton workflow](assets/comfyui-workflow.png)
 
+The prepared tensors use the `paiton-flux2-cache` volume; source weights and compiler caches use `paiton-flux2-cache-runtime`. Both persist across complete stop/start cycles.
+
 The helper pulls three public containers, downloads the pinned 5.46 GB checkpoint and prepares about 12 GB of runtime tensors once. Source weights are preserved. Downloads, prepared tensors, compilation caches and UI settings persist. No Hugging Face token or paid service is required.
 
 The first image loads and compiles the selected engine and can take several minutes. Later images reuse it. Switching engines unloads the previous model and incurs setup again. For comparisons, keep the prompt and seed fixed and choose **fixed** in the seed control.
 
-From `models/FLUX.2-klein`, run `./launch.sh --stop` to stop, `./launch.sh --logs` for logs, or `./launch.sh --ui simple` for a smaller prompt-and-image interface. Stopping preserves caches and outputs. The [complete model guide](https://github.com/Eliovp-BV/paiton-vllm-plugin/tree/paiton-flux2-klein-gfx1201-v1.0.0/models/FLUX.2-klein) covers terminal generation and using the node in an existing ComfyUI installation. This image package uses Diffusers; the same central repository also contains our vLLM text releases.
+From `models/FLUX.2-klein`, run `./launch.sh --stop` to stop, `./launch.sh --logs` for logs, or `./launch.sh --ui simple` for a smaller prompt-and-image interface. Stopping preserves caches and outputs. The [complete model guide](https://github.com/Eliovp-BV/paiton-vllm-plugin/tree/paiton-flux2-klein-gfx1201-v1.0.1/models/FLUX.2-klein) covers terminal generation and using the node in an existing ComfyUI installation. This image package uses Diffusers; the same central repository also contains our vLLM text releases.
 
 ## 12.9 GiB peak Torch allocation
 
@@ -98,7 +100,7 @@ The pinned runtime includes Torch 2.12.0 with ROCm 7.14, Diffusers 0.40.0 and Tr
 The quick start already contains these exact files. For a separate, versioned copy:
 
 ```bash
-hf download EliovpAI/FLUX.2-klein-4B-Paiton-RDNA4 --revision v1.0.0 --include 'artifacts/*' --local-dir ./paiton-flux2-hf
+hf download EliovpAI/FLUX.2-klein-4B-Paiton-RDNA4 --revision v1.0.1 --include 'artifacts/*' --local-dir ./paiton-flux2-hf
 ```
 
 Keep all six files in `artifacts/` together. They contain three shared libraries and their hash-checked compatibility manifests. They are loaded by the Paiton image runtime, not by `DiffusionPipeline.from_pretrained` as model weights.
@@ -110,9 +112,10 @@ mkdir -p paiton-images
 docker run --rm --device /dev/kfd --device /dev/dri \
   --group-add "$(stat -c '%g' /dev/kfd)" --shm-size 2g \
   -v paiton-flux2-cache:/models \
+  -v paiton-flux2-cache-runtime:/models/cache \
   -v "$PWD/paiton-flux2-hf/artifacts:/opt/paiton/image/artifacts:ro" \
   -v "$PWD/paiton-images:/outputs" \
-  ghcr.io/eliovp/paiton-vllm-plugin:flux2-klein-rdna4-v1.0.0 \
+  ghcr.io/eliovp/paiton-vllm-plugin:flux2-klein-rdna4-v1.0.1 \
   generate --prompt 'A fox in a woodland at sunrise, wildlife photograph' --seed 42
 ```
 

SHA256SUMS

@@ -1,8 +1,8 @@
-d032d165b20f77321938e6371d91345e67c3f3328f815ad3d4da1a58b35bf984  BENCHMARKS.md
+7ee29787618ca4b93981fb0214af433787334c331c16b64050e4b054e2b01de9  BENCHMARKS.md
 c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4  LICENSE
 92640fb97222fd0a698ff28ce0c3782c172623f8d6c609b557636a80f28fb946  LICENSES/Triton-MIT.txt
 3419cabb33500032ddf1adbb80d5e525adff6feeb0b42b6fe799d850bd860a06  NOTICE
-d5e5824b4a3d26005e45e631448f659bef20a226d09f8023c7a72e86d781d103  README.md
+51e4bf6eca8277ac9811da7ff6f742c1f0247182c3923b41c31f7f700dc2e11a  README.md
 dde1f76fa30cceb4487b492b61332b90ebb2b478b15a733fba12af3aaa2068b0  THIRD_PARTY_NOTICES.md
 693063398478a32235f27ffc9b324811c23d588c02f1283d148499d60da05484  artifacts/flux2_klein_decoder_gfx1201.manifest.json
 456f278c21a25445edd1d1d91196cd63f0f5ac7eb9bc0b146d503c526ea316cf  artifacts/flux2_klein_decoder_gfx1201.so
@@ -19,4 +19,4 @@ d957298bc2fb8a4f4870411968bc4319c169857f2d167d75508fba0766474b27  assets/product
 531be4d5692bb4867571df3e2fc40225a6c0b78284834b0daa449071be908adb  benchmark-data/comfyui-validation.json
 aa618807100cf1d5d3affbeffaf161314b933e8fc29933cf0f0a6b915a5be80d  benchmark-data/raw-timings.csv
 fbf4587152044ebbef956df16b46b9b22c9dec65940c881e666749d5721aad86  benchmark-data/results.json
-cd848e6f0d2430d9f8392ce98df05b25021bf8ca9eedefdc6eed0ae89b7dc6db  paiton-hub.json
+f6a192228680ae571e170a8e30ffd613471e20ec670f0f23f5b0306052a87d8f  paiton-hub.json

paiton-hub.json

@@ -1,12 +1,12 @@
 {
   "format_version": 1,
   "repository": "EliovpAI/FLUX.2-klein-4B-Paiton-RDNA4",
-  "version": "v1.0.0",
+  "version": "v1.0.1",
   "content": "Compiled runtime artifacts, manifests, notices, benchmark data and example media. No checkpoint weights.",
   "runtime_source": {
     "repository": "https://github.com/Eliovp-BV/paiton-vllm-plugin",
-    "revision": "0e20f1db97050f9eb83af0158f6c6d5bd329e0a1",
-    "tag": "paiton-flux2-klein-gfx1201-v1.0.0",
+    "revision": "56be0226cb18fec05c3d562b57bcbd752a9c66ea",
+    "tag": "paiton-flux2-klein-gfx1201-v1.0.1",
     "path": "models/FLUX.2-klein"
   },
   "source_checkpoint": {
@@ -16,19 +16,19 @@
   },
   "containers": {
     "klein": {
-      "tag": "ghcr.io/eliovp/paiton-vllm-plugin:flux2-klein-rdna4-v1.0.0",
-      "digest": "sha256:8866c8dd29d7dfbba81156a83af75229ffc9bc05a074833bc516d8da79ebd6a8",
-      "reference": "ghcr.io/eliovp/paiton-vllm-plugin@sha256:8866c8dd29d7dfbba81156a83af75229ffc9bc05a074833bc516d8da79ebd6a8"
+      "tag": "ghcr.io/eliovp/paiton-vllm-plugin:flux2-klein-rdna4-v1.0.1",
+      "digest": "sha256:994af1fdfa53d1f0b0a398bb247d4c1ac6caa93f4a56f22f90d961ca76e1f7de",
+      "reference": "ghcr.io/eliovp/paiton-vllm-plugin@sha256:994af1fdfa53d1f0b0a398bb247d4c1ac6caa93f4a56f22f90d961ca76e1f7de"
     },
     "tools": {
-      "tag": "ghcr.io/eliovp/paiton-vllm-plugin:flux2-tools-rdna4-v1.0.0",
-      "digest": "sha256:9268cb0505ba4db59adfa7f7faf87ccabf3803571757add7397da40752f453ba",
-      "reference": "ghcr.io/eliovp/paiton-vllm-plugin@sha256:9268cb0505ba4db59adfa7f7faf87ccabf3803571757add7397da40752f453ba"
+      "tag": "ghcr.io/eliovp/paiton-vllm-plugin:flux2-tools-rdna4-v1.0.1",
+      "digest": "sha256:d9ffefd705d5f010c65199a88a0240275aed06f2042a9b1f1d5b5a144d013e61",
+      "reference": "ghcr.io/eliovp/paiton-vllm-plugin@sha256:d9ffefd705d5f010c65199a88a0240275aed06f2042a9b1f1d5b5a144d013e61"
     },
     "comfyui": {
-      "tag": "ghcr.io/eliovp/paiton-vllm-plugin:flux2-comfyui-rdna4-v1.0.0",
-      "digest": "sha256:fdede6c2012be50b40207a04a6ed38b79b045b49267cf89180a0577e09de6fff",
-      "reference": "ghcr.io/eliovp/paiton-vllm-plugin@sha256:fdede6c2012be50b40207a04a6ed38b79b045b49267cf89180a0577e09de6fff"
+      "tag": "ghcr.io/eliovp/paiton-vllm-plugin:flux2-comfyui-rdna4-v1.0.1",
+      "digest": "sha256:b00940f1ee01ce4061b392395458aa0a3a48c51dad69794e16a5f24b8b20add3",
+      "reference": "ghcr.io/eliovp/paiton-vllm-plugin@sha256:b00940f1ee01ce4061b392395458aa0a3a48c51dad69794e16a5f24b8b20add3"
     }
   },
   "scope": {