From 659c79638c8a43a65940836f013beb91524fe187 Mon Sep 17 00:00:00 2001
From: biondizzle <biondizzle@gmail.com>
Date: Fri, 3 Apr 2026 11:08:29 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9C=85=20WORKING=20BUILD=20#43=20-=20GH200?=
 =?UTF-8?q?=20vLLM=20container=20builds=20successfully?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Versions locked:
- vLLM: v0.18.2rc0
- flashinfer: v0.6.7
- flash-attention: hopper branch
- lmcache: dev branch
- infinistore: main
- triton: 3.6.0 (PyPI wheel)
- Base: nvcr.io/nvidia/pytorch:26.03-py3 (PyTorch 2.11.0a0, CUDA 13.2.0)

DO NOT MODIFY WITHOUT MIKE'S APPROVAL
---
 vllm/Dockerfile | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/vllm/Dockerfile b/vllm/Dockerfile
index cef70f0..1cd43ec 100644
--- a/vllm/Dockerfile
+++ b/vllm/Dockerfile
@@ -1,3 +1,24 @@
+# ==============================================================================
+# ⚠️⚠️⚠️ WORKING BUILD - DO NOT TOUCH ⚠️⚠️⚠️
+# ==============================================================================
+# Build #43 succeeded on 2026-04-03 with these exact versions:
+#   - vLLM: v0.18.2rc0
+#   - flashinfer: v0.6.7
+#   - flash-attention: hopper branch
+#   - lmcache: dev branch
+#   - infinistore: main
+#   - triton: 3.6.0 (PyPI wheel)
+#   - Base: nvcr.io/nvidia/pytorch:26.03-py3 (PyTorch 2.11.0a0, CUDA 13.2.0)
+#
+# HARD RULES:
+#   1. NO DOWNGRADES - CUDA 13+, PyTorch 2.9+, vLLM 0.18.1+
+#   2. NO SKIPPING COMPILATION - Build from source
+#   3. CLEAR ALL CHANGES WITH MIKE BEFORE MAKING THEM
+#   4. ONE BUILD AT A TIME - Mike reports failure → I assess → I report
+#
+# If you need to modify this file, ask Mike first.
+# ==============================================================================
+
 # ---------- Builder Base ----------
 # Using NVIDIA NGC PyTorch container (26.03) with:
 # - PyTorch 2.11.0a0 (bleeding edge)