docs(inference_guide): validate Gemma-4-31B-it P4+D4 on Ascend 910B3 - #298
Open
EdisonSu768 wants to merge 2 commits into
Open
docs(inference_guide): validate Gemma-4-31B-it P4+D4 on Ascend 910B3#298EdisonSu768 wants to merge 2 commits into
EdisonSu768 wants to merge 2 commits into
Conversation
Deploying alauda-ai with
|
| Latest commit: |
6885cda
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://8b0fe7fa.alauda-ai.pages.dev |
| Branch Preview URL: | https://docs-gemma4-31b-it-pd-aiperf.alauda-ai.pages.dev |
EdisonSu768
force-pushed
the
docs/gemma4-31b-it-pd-aiperf
branch
from
August 3, 2026 12:55
a2b2013 to
6885cda
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 a validated inference-guide page and deployment manifest for Gemma-4-31B-it. Deployment and benchmark evidence come from
model-autocommitsdcad16cand966538don the Guian Ascend 910B3 cluster.Validated stack
google/gemma-4-31B-it, BF16 text-generation path.quay.io/ascend/vllm-ascend:nightly-main-openeuler-0721(vLLM 0.25.1, CANN 9.0.1).MooncakeConnectorV1with Ascend Direct KV transfer.AIPerf results
AIPerf 0.7.0, closed loop, concurrency 8/16/32, 480 requests per tier. All six tiers completed with 0 errors.
Throughput and ITL are flat from concurrency 8 onward. The service is Prefill-capacity-bound at roughly 8k input-dominated tokens/s; higher concurrency increases TTFT without increasing throughput.
Scheduler correction
The delivered manifest removes the tokenizer plugin and sidecar. This deployment has one fixed P/D pair and no prefix-cache producer, so tokenizer-based routing adds no choice. Hermes Router 26.6.0-rc.3 used a 5-second initialization deadline while the Gemma tokenizer cold-loaded in 17.59 seconds, causing endless retries. The live scheduler rolled from 2/2 to 1/1 Ready without restarting the 11-day-old Prefill/Decode Pods, and direct P/D smoke remained HTTP 200.
Validation
yarn lint: 0 errors, 0 warnings.git diff --checkpassed.