Add EAGLE-3 end-to-end speculative-decode test

[digantdesai]

Tiny matching target + draft on CPU drive the shifted method-flow the runner
implements -- prefill, draft chain, target_verify, accept, reseed -- and the
generated tokens are checked against greedy decoding (lossless by construction).
Forced-acceptance cases pin the partial, full, and accepted-EOS paths plus the
one-token budget; the random-weight loop alone can leave them uncovered.

This covers the decoding algorithm on CPU only; the CUDA/AOTI export (export.py)
and the C++ runner are exercised manually. Registered in pytest.ini next to the
draft/speculator unit tests.

Authored with assistance from Claude Code.

[digantdesai]

Stack from ghstack (oldest at bottom):

• Update tokenizers submodule to the linear-time HF encode path #20349
• Add --prompt_file flag to the eagle3 runner #20348
• Add chunked prefill to the eagle3 runner for prompts past the ring-cache cap #20347
• Fix sliding-window chunked prefill in the gemma4-31B runner #20346
• Make EAGLE-3 chain length K a runtime parameter #20345
• Add split-K mid-M SDPA Triton kernel for EAGLE-3 target_verify at long context #20344
• -> Add EAGLE-3 end-to-end speculative-decode test #20157
• Add the EAGLE-3 speculative-decoding runner (CUDA) #20156
• Add the EAGLE-3 speculator CUDA export #20155
• Add a weight-stationary INT4 GEMM for small M #20154
• Add the Eagle3Speculator module for speculative decoding #20153
• Add KV cache to the EAGLE-3 draft head #20152
• Add Gemma4 EAGLE-3 eager reference #20151
• Add Gemma4 EAGLE-3 hidden-state taps #20150
• Add EAGLE-3 draft head #20149

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20157

• 📄 Preview Python docs built from this PR

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

❌ 3 New Failures, 1 Cancelled Job, 2 Unrelated Failures, 2 Unclassified Failures

As of commit 163323d with merge base dc55469 ():

NEW FAILURES - The following jobs have failed:

• pull / test-arm-backend-no-driver (test_pytest_models_tosa) / linux-job (gh)
  RuntimeError: Command docker exec -t e170912b3f2913c2d4e559a86abcdc4de77d9fb7fb6515c5600138ded19b8042 /exec failed with exit code 1
• pull / test-multimodal-linux (gemma3-4b) / linux-job (gh)
  RuntimeError: Command docker exec -t 6f83715f1d2fccf271e230d5aec8d421bb5e56161fb1c425fb80f084f60de85a /exec failed with exit code 139
• pull / test-phi-3-mini-runner-linux / linux-job (gh)
  RuntimeError: Command docker exec -t e0bc733a4c7cd31082374943cd167e2f7c538326d30ba81a44f6035fe6c552c5 /exec failed with exit code 1

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:

• Build Aarch64 Linux Wheels / pytorch/executorch / build-wheel-py3_10-cpu-aarch64 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
• Build Aarch64 Linux Wheels / pytorch/executorch / upload / upload-wheel-py3_10-cpu-aarch64 (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
  Unable to download artifact(s): Artifact not found for name: pytorch_executorch__3.10_cpu_aarch64

CANCELLED JOB - The following job was cancelled. Please retry:

• pull / unittest-nxp-neutron / linux-job (gh)

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• pull / test-moshi-linux / linux-job (gh) (matched linux rule in flaky-rules.json)
  E: Failed to fetch http://archive.ubuntu.com/ubuntu/pool/main/m/mesa/mesa-vdpau-drivers_23.2.1-1ubuntu3.1%7e22.04.3_amd64.deb 404 Not Found [IP: 172.66.152.176 80]
• pull / unittest-editable / windows / windows-job (gh) (matched win rule in flaky-rules.json)
  ##[error]The operation was canceled.

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