examples/models/gemma4_31b: CUDA Engine/Session adapter + OpenAI serving#20207
Draft
mergennachin wants to merge 2 commits into
Draft
examples/models/gemma4_31b: CUDA Engine/Session adapter + OpenAI serving#20207mergennachin wants to merge 2 commits into
mergennachin wants to merge 2 commits into
Conversation
[ghstack-poisoned]
Contributor
Author
mergennachin
requested review from
GregoryComer,
JacobSzwejbka,
SS-JIA,
abhinaykukkadapu,
digantdesai,
kimishpatel,
kirklandsign,
larryliu0820,
manuelcandales,
psiddh,
rascani,
robert-kalmar and
shoumikhin
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20207
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 6 New Failures, 10 Pending, 2 Unrelated FailuresAs of commit 142ff89 with merge base f0dff03 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This was referenced Jun 10, 2026
|
|
meta-cla
Bot
added
the
CLA Signed
[ghstack-poisoned]
mergennachin
added a commit
that referenced
this pull request
Jun 12, 2026
Adds the Gemma 4 31B serving path, mirroring qwen3_5_moe: a CUDA Engine/Session adapter (chunked prefill, per-session mutable rebinding, in-graph sampling) behind the model-agnostic LLMEngine/LLMSession contract, a JSONL worker, and a serve.py launcher. The generic worker loop gains an optional prompt_prefix_ids (Gemma BOS prepend) and serving_chat a matching prompt_token_offset so the context count stays honest. export.py emits get_mutable_buffer_metadata and prefill-chunk bounds for multi-session. ghstack-source-id: c21c647 ghstack-comment-id: 4674805750 Pull-Request: #20207
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds the Gemma 4 31B serving path, mirroring qwen3_5_moe: a CUDA
Engine/Session adapter (chunked prefill, per-session mutable rebinding,
in-graph sampling) behind the model-agnostic LLMEngine/LLMSession
contract, a JSONL worker, and a serve.py launcher. The generic worker
loop gains an optional prompt_prefix_ids (Gemma BOS prepend) and
serving_chat a matching prompt_token_offset so the context count stays
honest. export.py emits get_mutable_buffer_metadata and prefill-chunk
bounds for multi-session.