exo(1)

💅 exo(1) · NAME 💅

exo-dedicated-inference-deployment-create — Create AI deployment

okay so bestie, this is the manual page for exo(1), and this specific command is the one that creates an AI deployment. More specifically: it creates an AI deployment on dedicated inference servers. Slay.

---

✨ SYNOPSIS ✨

exo dedicated-inference deployment create [NAME] [flags]

---

🦋 DESCRIPTION 🦋

This command creates an AI deployment on dedicated inference servers. That’s the whole plot, no cap 💖.

---

🎀 OPTIONS 🎀

• --gpu-count=0 — Number of GPUs — keep it in the (1-8) lane.
• --gpu-type="" — GPU type family, e.g. gpua5000, gpu3080ti.
• -h, --help[=false] — help for create — the classic.
• --inference-engine-parameter-help[=false] — Show inference engine parameters help.
• --inference-engine-params="" — Space-separated inference engine server CLI arguments, e.g. "--gpu-memory-usage=0.8 --max-tokens=4096".
• --inference-engine-version="" — Inference engine version.
• --model-id="" — Model ID (UUID).
• --model-name="" — Model name (as created).
• --replicas=0 — Number of replicas (>=1).
• -z, --zone="" — zone.

---

🫶 OPTIONS INHERITED FROM PARENT COMMANDS 🫶

These are inherited from the parent commands, bestie:

• -C, --config="" — Specify an alternate config file [env EXOSCALE_CONFIG].
• -O, --output-format="" — Output format (table|json|text), see "exo output --help" for more information.
• --output-template="" — Template to use if output format is "text".
• -Q, --quiet[=false] — Quiet mode (disable non-essential command output).
• --timeout=15s — Per-zone timeout for list operations; -1s disables timeout [env EXOSCALE_TIMEOUT].
• -A, --use-account="" — Account to use in config file [env EXOSCALE_ACCOUNT].

---

👀 SEE ALSO 👀

• exo-dedicated-inference-deployment(1)

---

📜 HISTORY 📜

• 1-Jan-1980 — Auto generated by spf13/cobra.

---

💖 That’s the whole manual! Source/version: Auto generated by spf13/cobra. Date: Jan 1980. Manual: exo(1). Byeee 🫶✨