ruihan/qwen38-flash-next-rtx6000d
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Deploy audited RTX 6000D Flash-Next 128K multimodal baseline

Browse Source
This commit is contained in:
ruihan
2026-09-18 10:47:26 +08:00
commit 7e53821920
45 changed files with 1745 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+4
View File
@@ -0,0 +1,4 @@
FROM vllm/vllm-openai@sha256:c4392d76e3eec8983fa152651365158cb062e348fd40398963f499d5867b9e28
COPY patches/ /opt/6000d-patches/
RUN python3 /opt/6000d-patches/fix_prefix_alignment.py
LABEL org.opencontainers.image.description="Audited NVIDIA Flash-Next baseline for RTX 6000D"