Qwen3.6-27B recipe and README optimized for agentic coding #recipebot#267
Draft
jawadaminGOOG wants to merge 1 commit into
Draft
Qwen3.6-27B recipe and README optimized for agentic coding #recipebot#267jawadaminGOOG wants to merge 1 commit into
jawadaminGOOG wants to merge 1 commit into
Conversation
- Keep final deployment manifests in gke/ and standard 5-step contribution-ready README. - Include official uBench benchmark results and standard Serving Benchmark Result table. - Remove experimental subfolders (moved to standalone repository). UBENCH Results (Cloud TPU v6e-4): - uBench Run ID: vllm_inference-qwen3_32b-fp8-2026-07-13_194548-04391392-a560-424f-a308-e71e591ac9c9 - Jobset Name: jawadamin-ubench-dw8wrtyo - Model: Qwen/Qwen3.6-27B-FP8 - Request Throughput: 28.07 req/s - TTFT P50: 4529.76 ms - Output Token Throughput: 3233.91 tokens/s (404.24 tokens/s/chip) TAG=agy CONV=a3f7389e-c990-4e97-b884-73a3e79ea117
jawadaminGOOG
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR contains modular recipes to deploy, optimize, and integrate the Qwen/Qwen3.6-27B-FP8 model on Google Kubernetes Engine (GKE) targeting Cloud TPU v6e-4 (4 chips, 2x2 topology) with vLLM.
UBENCH Results (Cloud TPU v6e-4):