[executorch][llm] Share the batching executors' session logic under extension/llm/batching/util

[Gasoonjia]

Stack from ghstack (oldest at bottom):

• [executorch][muse] Move off-graph KV to the batching path and test batching in OSS CI #23375
• [executorch][muse] Add run_solo_batching #23374
• [executorch][muse] Add export_solo_batching.py #23373
• [executorch][cuda] Let CudaExecutor honor a program's prefill lower bound #23372
• -> [executorch][llm] Share the batching executors' session logic under extension/llm/batching/util #23371
• [executorch][cuda] Add CudaExecutor #23370
• [executorch][cuda] Add step_plan for the CUDA batching executor #23369
• [executorch][llm] Add Buck targets for extension/llm/batching #23368
• [executorch][cuda] Add CudaCellCache #23367
• [executorch][cuda] Lower off-graph KV in a cell layout #23366
• [executorch][cuda] Extract CudaKVPool from CudaSequenceKVCache #23365

ModuleExecutor and CudaExecutor (previous diff) carried copies of the same
logic. It moves into util::SessionTable, which both now use:

• sessions: open/close/clone over the cache's BatchControl, bounded by
  max_sessions, with session ids never reused;
• pack(BatchInput): flattens a batch onto one token axis with a per-sequence
  cursor, so consecutive chunks of a prompt abut, and truncates reopened
  sequences only after every input has checked out;
• per-session sampling: one Sampler per generation, drawing a session's token
  from its logits row.

Plus util::select_rows, the logits rows a forward over one slice of a packed
batch selects.

What stays in each executor is what differs: how the program is read and
validated, and how slices map onto methods (one forward for ModuleExecutor;
decode/prefill for CudaExecutor).

No behavior change. Log messages from the moved code now say pack: rather
than build_step:.

Builds as extension_llm_batching_util (CMake) and
//executorch/extension/llm/batching:session_table (Buck).

Differential Revision: D123051482

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/23371

• 📄 Preview Python docs built from this PR

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

❌ 7 New Failures, 1 Pending, 3 Unclassified Failures

As of commit f2c231d with merge base c16dd0a ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner (gh)
  >>> Lint for extension/llm/batching/util/session_table.cpp:
• pull / unittest / linux / linux-job (gh)
  .ci/scripts/tests/test_wheel_test_modules.py::TestDroppedTestModules::test_ci_entry_points_still_match_the_workflows
• pull / unittest / macos / macos-job (gh)
  .ci/scripts/tests/test_wheel_test_modules.py::TestDroppedTestModules::test_ci_entry_points_still_match_the_workflows
• pull / unittest / windows / windows-job (gh)
  .ci/scripts/tests/test_wheel_test_modules.py::TestDroppedTestModules::test_ci_entry_points_still_match_the_workflows
• pull / unittest-editable / linux / linux-job (gh)
  .ci/scripts/tests/test_wheel_test_modules.py::TestDroppedTestModules::test_ci_entry_points_still_match_the_workflows
• pull / unittest-editable / macos / macos-job (gh)
  .ci/scripts/tests/test_wheel_test_modules.py::TestDroppedTestModules::test_ci_entry_points_still_match_the_workflows
• pull / unittest-editable / windows / windows-job (gh)
  .ci/scripts/tests/test_wheel_test_modules.py::TestDroppedTestModules::test_ci_entry_points_still_match_the_workflows

UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:

• Test CUDA Builds / unittest-cuda / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  backends/cuda/tests/test_offgraph_kv.py::OffGraphKVCellCompileTest::test_decode_and_prefill_from_two_tokens_lower
• Test CUDA Builds / unittest-cuda-runtime / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  [ FAILED ] CudaKVCacheTest.CacheOutlivesTheStreamItLastSteppedOn
• Test ROCm AOTI / unittest-rocm-gfx950-rocm7.2 / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  backends/cuda/tests/test_offgraph_kv.py::OffGraphKVCellCompileTest::test_decode_and_prefill_from_two_tokens_lower

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

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.