deprecate prompt cache in sdk/cli

[mitali401]

Emit user warning for disabled_prompt_cache or --no-prompt-cache params

poetry run together endpoints create \
  --model "meta-llama/Llama-3-8b-chat-hf" \
  --gpu h100 \
  --gpu-count 1 \
  --min-replicas 1 \
  --max-replicas 1 \
  --no-prompt-cache \
  --no-speculative-decoding
/Users/MMeratwal/Library/Application Support/pypoetry/venv/lib/python3.9/site-packages/urllib3/__init__.py:35: NotOpenSSLWarning: urllib3 v2 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'. See: https://github.com/urllib3/urllib3/issues/3020
  warnings.warn(
/Users/MMeratwal/Desktop/together-python/src/together/cli/api/endpoints.py:175: UserWarning: The 'disable_prompt_cache' parameter (CLI flag: '--no-prompt-cache') is deprecated and will be removed in a future version.
  response = client.endpoints.create(
Created dedicated endpoint with:
  Model: meta-llama/Llama-3-8b-chat-hf
  Min replicas: 1
  Max replicas: 1
  Hardware: 1x_nvidia_h100_80gb_sxm
  Prompt cache: disabled
  Speculative decoding: disabled
Endpoint created successfully, id: endpoint-8b513273-1545-4c43-9843-502e2b3f1ebf
Waiting for endpoint to be ready...

closes: https://linear.app/together-ai/issue/MLE-2917/emit-user-warning-for-using-prompt-cache-param

[atihkin]

lgtm