Cookbook: clearer tooltips on saved-config badge and GPU chip (#850)

Two small polish items in the Cookbook Serve panel.

Saved-config badge
The little count badge next to the Save button ("3 ▾" etc.) had a
generic "Saved launch configs" tooltip, so the number reads like a
notification dot. Make it spell out what it is and what clicking does:
"3 saved launch configs for <model> — click ▾ to load or delete"
(and "No saved launch configs for <model> yet — click Save to add
one" when empty). Tooltip stays in sync via _updateSavedToggleLabel
so save/delete updates both the count and the hint.

GPU chip on mixed-GPU boxes (#711)
The chip label was `${gpuCount}x ${gpu_name}`, where gpu_name is
just gpus[0].name — so a 4090 + 3060 reads as "2x RTX 4090". The
backend already emits gpu_groups (identical cards grouped, used by
the serve flow to pin CUDA_VISIBLE_DEVICES) and a per-card gpus[]
array, so use them:

- Label renders each homogeneous pool: "1× RTX 4090 + 1× RTX 3060".
  Homogeneous setups keep the existing "2× RTX 4090" form.
- Tooltip lists each GPU with its index + VRAM, useful for picking
  the right device when launching.

Refs #711.

static/style.css

@@ -20215,6 +20215,19 @@ body.gallery-selecting .gallery-dl-btn,
   display: inline-flex;
   align-items: center;
   gap: 3px;
+  /* Cap chip width so a long label (e.g. heterogeneous GPU group
+     "1× RTX 4090 + 1× RTX 3060") wraps to the next row instead of
+     overflowing the modal. Full text stays in the tooltip. */
+  max-width: 100%;
+}
+.hwfit-hw-chip-toggle {
+  /* Allow the chip body to truncate with an ellipsis when the chip
+     itself is capped at its container's width. Without this, the
+     toggle button keeps its intrinsic width and pushes the × button
+     off-screen on narrow viewports. */
+  max-width: 100%;
+  overflow: hidden;
+  text-overflow: ellipsis;
 }
 .hwfit-hw-chip button,
 .hwfit-hw-chip-dismiss,