Set max cache seq len in generate recipe

[SalmanMohammadi]

Context

What is the purpose of this PR? Is it to

• add a new feature
• fix a bug
• update tests and/or documentation
• other (please add here)

#1581

Changelog

We only need a cache size of prompt_len + max_generated_tokens for the generate recipe. This utilizes #1449 to significantly reduce unnecessary memory consumption.

Tested on a 4090 with Llama3.1 8B:
On this branch

INFO:torchtune.utils._logging:Time for inference: 4.57 sec total, 25.39 tokens/sec
INFO:torchtune.utils._logging:Bandwidth achieved: 413.58 GB/s
INFO:torchtune.utils._logging:Memory used: 16.43 GB

on main:

torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 1024.00 MiB. GPU 0 has a total capacity of 23.64 GiB of which 62.81 MiB is free. 
Process 539192 has 23.57 GiB memory in use. Of the allocated memory 23.02 GiB is allocated by PyTorch, and 121.49 MiB is reserved by PyTorch but unallocated. 
If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)

Test plan

Please make sure to do each of the following if applicable to your PR. (If you're not sure about any one of these just ask and we will happily help. We also have a contributing page for some guidance on contributing.)

• run pre-commit hooks and linters (make sure you've first installed via pre-commit install)
• add unit tests for any new functionality
• update docstrings for any new or updated methods or classes
• run unit tests via pytest tests
• run recipe tests via pytest tests -m integration_test
• manually run any new or modified recipes with sufficient proof of correctness
• include relevant commands and any other artifacts in this summary (pastes of loss curves, eval results, etc.)

UX

If your function changed a public API, please add a dummy example of what the user experience will look like when calling it.
Example of docstring: https://github.com/pytorch/torchtune/blob/6a7951f1cdd0b56a9746ef5935106989415f50e3/torchtune/modules/vision_transformer.py#L285
Example in our docs: https://pytorch.org/torchtune/main/tutorials/qat_finetune.html#applying-qat-to-llama3-models

• I did not change any public API;
• I have added an example to docs or docstrings;

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchtune/1603

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• linux-aarch64 CI tests are being timed out resulting in test failures

✅ No Failures

As of commit 0fdc46f with merge base 1e9dc42 ():
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[joecummings]

zoom zoom

[joecummings]

This is brilliant