RIP Cost Benefit

.github/workflows/restore_cost_benefit.yml

@@ -1,92 +0,0 @@
-# .github/workflows/restore_cost_benefit.yml
-name: Restore src/cost_benefit.py
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-    branches: [main]
-
-jobs:
-  restore:
-    runs-on: ubuntu-latest
-    # allow the GITHUB_TOKEN to push a commit back
-    permissions:
-      contents: write
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-        with:
-          # you need the token available for the later push
-          token: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Recreate src/cost_benefit.py
-        run: |
-          mkdir -p src
-          cat > src/cost_benefit.py <<'PY'
-          import argparse
-          import subprocess
-          import time
-          import requests
-          
-          def detect_available_budget(runtime_env: str) -> int:
-              """
-              Return an approximate VRAM‑based budget (MB) when running locally,
-              else default to 100.
-              """
-              import torch
-              if "local" in runtime_env and torch.cuda.is_available():
-                  total_vram_mb = torch.cuda.get_device_properties(0).total_memory // (1024 ** 2)
-                  return min(total_vram_mb, 100)
-              return 100
-          
-          def get_best_model(runtime_env: str, *, use_local_only: bool = False, use_api_only: bool = False) -> dict:
-              """
-              Pick the fastest model that fits in the detected budget while
-              respecting the locality filters.
-              """
-              static_costs = {
-                  "llama3.2":  {"size": 20, "token_cost": 0.0001, "tokens_sec": 30, "type": "local"},
-                  "mistral":   {"size": 40, "token_cost": 0.0002, "tokens_sec": 50, "type": "local"},
-                  "gemini-2.0-flash":            {"size": 60, "token_cost": 0.0005, "tokens_sec": 60, "type": "api"},
-                  "gemini-2.5-pro-preview-03-25": {"size": 80, "token_cost": 0.002 , "tokens_sec": 45, "type": "api"},
-              }
-          
-              budget = detect_available_budget(runtime_env)
-              best_model, best_speed = None, -1
-          
-              for model, info in static_costs.items():
-                  if info["size"] > budget:
-                      continue
-                  if use_local_only and info["type"] != "local":
-                      continue
-                  if use_api_only and info["type"] != "api":
-                      continue
-                  if info["tokens_sec"] > best_speed:
-                      best_model, best_speed = model, info["tokens_sec"]
-          
-              chosen = best_model or "llama3.2"  # sensible default
-              return {
-                  "model": chosen,
-                  "token_cost": static_costs[chosen]["token_cost"],
-                  "tokens_sec": static_costs[chosen]["tokens_sec"],
-                  "note": None if best_model else "Defaulted because no model met the constraints",
-              }
-          PY
-
-      - name: Commit & push only when the file was missing
-        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        run: |
-          set -e
-          git config user.name  "HARSHIL PATEL"
-          git config user.email "hpppatel@ucdavis.edu"
-
-          # If the file is NOT in the current Git index, add‑commit‑push.
-          if ! git ls-files --error-unmatch src/cost_benefit.py >/dev/null 2>&1; then
-            git add src/cost_benefit.py
-            git commit -m "chore(ci): restore missing src/cost_benefit.py [skip ci]"
-            git push origin HEAD:main
-          else
-            echo "src/cost_benefit.py already exists in the repository – nothing to restore"
-          fi

src/cost_benefit.py

@@ -1,48 +0,0 @@
-import argparse
-import subprocess
-import time
-import requests
-
-def detect_available_budget(runtime_env: str) -> int:
-    """
-    Return an approximate VRAM‑based budget (MB) when running locally,
-    else default to 100.
-    """
-    import torch
-    if "local" in runtime_env and torch.cuda.is_available():
-        total_vram_mb = torch.cuda.get_device_properties(0).total_memory // (1024 ** 2)
-        return min(total_vram_mb, 100)
-    return 100
-
-def get_best_model(runtime_env: str, *, use_local_only: bool = False, use_api_only: bool = False) -> dict:
-    """
-    Pick the fastest model that fits in the detected budget while
-    respecting the locality filters.
-    """
-    static_costs = {
-        "llama3.2":  {"size": 20, "token_cost": 0.0001, "tokens_sec": 30, "type": "local"},
-        "mistral":   {"size": 40, "token_cost": 0.0002, "tokens_sec": 50, "type": "local"},
-        "gemini-2.0-flash":            {"size": 60, "token_cost": 0.0005, "tokens_sec": 60, "type": "api"},
-        "gemini-2.5-pro-preview-03-25": {"size": 80, "token_cost": 0.002 , "tokens_sec": 45, "type": "api"},
-    }
-
-    budget = detect_available_budget(runtime_env)
-    best_model, best_speed = None, -1
-
-    for model, info in static_costs.items():
-        if info["size"] > budget:
-            continue
-        if use_local_only and info["type"] != "local":
-            continue
-        if use_api_only and info["type"] != "api":
-            continue
-        if info["tokens_sec"] > best_speed:
-            best_model, best_speed = model, info["tokens_sec"]
-
-    chosen = best_model or "llama3.2"  # sensible default
-    return {
-        "model": chosen,
-        "token_cost": static_costs[chosen]["token_cost"],
-        "tokens_sec": static_costs[chosen]["tokens_sec"],
-        "note": None if best_model else "Defaulted because no model met the constraints",
-    }