nitpick - EOF is not a signal, it just flushes the current line content without needing a newline in cooked mode and doing this on an empty line results in a 0 byte read(), which most apps interpret as EOF
and the terminal emulator is not itself sending the signals, its always just sending raw characters to the pty device - it is the kernel's pty layer sending a signal if the right flags are on and doing line buffering, local echo, etc. and signals go to the foreground process group (which is set by the shell making a tcsetpgrp syscall)
unfortunately disabling temperature / switching to greedy sampling doesn't necessarily make most LLM inference engines _fully_ deterministic as parallelism and batching can result in floating point error accumulating differently from run to run - it's possible to make them deterministic but does come with a perf hit
some providers _do_ let you set the temperature, including to "zero", but most will not take the perf hit to offer true determinism
possible - but KV caches are generally _much_ bigger than the source text and can be reproduced from the source text so it wouldn't make a lot of sense to throw it out
pcie devices can also do direct transfers to each other - if you have one of these and a gpu its relatively quick to move data between them without bouncing through main ram