Ripple advertises a 1M context window, but `tokenizer_config.json` declares 131,072 tokens while `config.json` declares 2,097,152. Tokenizer-based clients can consequently validate or truncate inputs at 128Ki.
Set both declared limits to 1,048,576 tokens and state the exact 1Mi limit in the model card.
Validation: both JSON files parse, their context limits agree at 1,048,576, and the diff is limited to those two metadata values and the model-card wording.
Apply the server changes from ripple-inference PR #18 (08fd9f4383). Default target context to 1048576, retain draft window 16384, and enable the stock SGLang positional-limit override required for the draft. Update the server README.
https://github.com/ricursive/ripple-inference/pull/18
Fix dropped parallel tool calls in speculative streams
Apply ripple-inference PR #17 (d68cca40e1). Reconcile streamed tool calls at finish so speculative deltas cannot drop trailing calls or argument suffixes. Validated with CPU parser and chat-format regression tests on stock SGLang 0.5.19.
https://github.com/ricursive/ripple-inference/pull/17
