Final Deploy: Swapped wheel source to generic linux AVX2

Dockerfile

@@ -1,37 +1,38 @@
-# Base Image
+# Start with Python 3.11
 FROM python:3.11
 
-# Set Working Directory
+# Working Directory Setup
 WORKDIR /app
 
-# System tools install karo
+# Install basic tools (Quick step)
 RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
     cmake \
     libgl1 \
     && rm -rf /var/lib/apt/lists/*
 
-# === ⚡ MAGIC FIX ⚡ ===
-# Hum pip ko upgrade karke batayenge ki sirf Binary (bana-banaya) chahiye.
-# Hum version v0.2.90 use kar rahe hain jo sabse stable hai free servers ke liye.
+# === 🛡️ THE FINAL FIX: CORRECT WHEEL INSTALL ===
+# Ye link (jllllll/AVX2/cpu) specially HF jaise servers ke liye hai.
+# 1. Compile nahi karega (Fast install).
+# 2. 'manylinux' wheel uthayega (No 'musl' error crash).
 RUN pip install --upgrade pip && \
     pip install llama-cpp-python==0.2.90 \
-    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu \
+    --extra-index-url https://jllllll.github.io/llama-cpp-python-cuBLAS-wheels/AVX2/cpu \
     --prefer-binary \
     --no-cache-dir
 
-# Baaki requirements copy karo aur install karo
+# Install remaining dependencies from requirements.txt
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy Code
+# Copy App Code
 COPY . .
 
-# Permissions set karo
+# Set Permissions
 RUN chmod -R 777 /app
 
-# Expose Port
+# Open Port
 EXPOSE 7860
 
-# Run Server
+# Launch
 CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "7860"]