freesolo-flash-dev 1.2.118__tar.gz → 1.2.119__tar.gz

{freesolo_flash_dev-1.2.118 → freesolo_flash_dev-1.2.119}/.github/workflows/deploy-modal-dev.yml

@@ -86,7 +86,8 @@ jobs:
             deploy=true
           elif ! changed="$(git diff --name-only "$last_deployed_sha" "$CURRENT_SHA" 2>/dev/null)"; then
             deploy=true
-          elif grep -qE '^(flash/|pyproject\.toml$|uv\.lock$|\.github/workflows/deploy-modal-dev\.yml$)' <<<"$changed"; then
+          # the build-time vllm repair lives outside flash/, so name its exact image input path.
+          elif grep -qE '^(flash/|docker/patch_vllm_moe_lora\.py$|pyproject\.toml$|uv\.lock$|\.github/workflows/deploy-modal-dev\.yml$)' <<<"$changed"; then
             deploy=true
           fi
           echo "deploy=$deploy" >> "$GITHUB_OUTPUT"

{freesolo_flash_dev-1.2.118 → freesolo_flash_dev-1.2.119}/.github/workflows/deploy-modal.yml

@@ -118,8 +118,9 @@ jobs:
           # any `flash/` change, not just `flash/serving/`: the image ships the whole package via
           # `add_local_python_source("flash")`, so a change anywhere under flash/ can alter what runs
           # in the container. narrowing this to flash/serving/ would let the deployed app drift from
-          # the merged source. pyproject/uv.lock gate the image's dependency bounds.
-          elif grep -qE "^(flash/|pyproject\.toml$|uv\.lock$|\.github/workflows/deploy-modal\.yml$)" <<< "$changed"; then
+          # the merged source. pyproject/uv.lock gate dependency bounds, and the build-time vllm
+          # repair lives outside flash/, so its exact path must trigger a rebuild too.
+          elif grep -qE "^(flash/|docker/patch_vllm_moe_lora\.py$|pyproject\.toml$|uv\.lock$|\.github/workflows/deploy-modal\.yml$)" <<< "$changed"; then
             deploy=true
           fi
           echo "deploy=$deploy" >> "$GITHUB_OUTPUT"

{freesolo_flash_dev-1.2.118 → freesolo_flash_dev-1.2.119}/.github/workflows/publish-serving-image.yml

@@ -85,7 +85,8 @@ jobs:
       # while the tags keep pointing at the old one. that is the whole COPY set -- `flash`, the
       # lockfile, the launcher, and the files copied alongside them -- plus `.dockerignore`, which
       # decides what the build context contains at all, and this workflow file, so a change to the
-      # build here republishes rather than leaving the old image serving under the same tags.
+      # build here republishes rather than leaving the old image serving under the same tags. the
+      # build-time vllm repair lives outside flash/, so its exact path is an explicit image input.
       - name: Decide whether to publish
         id: gate
         working-directory: .
@@ -127,7 +128,7 @@ jobs:
             publish=true
           elif ! changed="$(git diff --name-only "$last_published_sha" "$CURRENT_SHA" 2>/dev/null)"; then
             publish=true
-          elif grep -qE "^(flash/|Dockerfile\.serve$|\.dockerignore$|serve_launch\.py$|pyproject\.toml$|uv\.lock$|README\.md$|LICENSE$|NOTICE$|\.github/workflows/publish-serving-image\.yml$)" <<< "$changed"; then
+          elif grep -qE "^(flash/|docker/patch_vllm_moe_lora\.py$|Dockerfile\.serve$|\.dockerignore$|serve_launch\.py$|pyproject\.toml$|uv\.lock$|README\.md$|LICENSE$|NOTICE$|\.github/workflows/publish-serving-image\.yml$)" <<< "$changed"; then
             publish=true
           fi
           echo "publish=$publish" >> "$GITHUB_OUTPUT"

{freesolo_flash_dev-1.2.118 → freesolo_flash_dev-1.2.119}/CHANGELOG.md

@@ -73,6 +73,8 @@ This file starts at 1.1.35. Earlier releases are not reconstructed here; use
 
 ### Fixed
 
+- Qwen3.6 FP8 MoE serving now preserves unquantized activations for LoRA A while keeping the base
+  MoE path quantized, backporting the exact vLLM PR #42120 behavior into the pinned 0.23.0 image.
 - GRPO publication now validates complete finite optimizer-step actor gradient norms instead of
   masked advantage-bound spread, so valid truncated groups are not falsely rejected and deployable
   checkpoints remain withheld until terminal evidence validation succeeds.

{freesolo_flash_dev-1.2.118 → freesolo_flash_dev-1.2.119}/Dockerfile.serve

@@ -26,10 +26,14 @@ RUN python -c 'import sys; assert sys.version_info[:2] == (3, 12)' \
 
 COPY pyproject.toml uv.lock README.md LICENSE NOTICE ./
 COPY flash ./flash
+COPY docker/patch_vllm_moe_lora.py ./docker/patch_vllm_moe_lora.py
 COPY serve_launch.py ./serve_launch.py
 RUN uv sync --frozen --no-dev --extra serve-runtime
+RUN /opt/flash-venv/bin/python /app/docker/patch_vllm_moe_lora.py \
+    && /opt/flash-venv/bin/python /app/docker/patch_vllm_moe_lora.py --verify \
+    && rm /app/docker/patch_vllm_moe_lora.py
 
-# The CUDA this image runs on is decided by vllm's own compiled extension, not by us: every vllm
+# the cuda this image runs on is decided by vllm's own compiled extension, not by us: every vllm
 # wheel from 0.20.2 onward (0.23.0 included) ships a vllm/_C.abi3.so linked against
 # libcudart.so.13. Measured across the published wheels -- 0.19.1 links libcudart.so.12, 0.20.2 and
 # later link .13 -- so no pin inside the 0.2x line escapes CUDA 13, and downgrading torch to a

{freesolo_flash_dev-1.2.118 → freesolo_flash_dev-1.2.119}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: freesolo-flash-dev
-Version: 1.2.118
+Version: 1.2.119
 Summary: Flash — managed LoRA post-training (SFT/GRPO/OPD) for Freesolo environments, driven by the `flash` CLI
 Project-URL: Homepage, https://github.com/freesolo-co/flash
 Project-URL: Repository, https://github.com/freesolo-co/flash