Skip to content

perf(cuda): dense Q4_K batched prefill + decode SoA — Qwen3-8B 61.2→432 prefill, 65→74.7 decode (#156/#158/#160)#161

Merged
pekkah merged 9 commits into
masterfrom
perf/cuda-dense-q4k-batched-prefill-156
Jun 6, 2026
Merged

perf(cuda): dense Q4_K batched prefill + decode SoA — Qwen3-8B 61.2→432 prefill, 65→74.7 decode (#156/#158/#160)#161
pekkah merged 9 commits into
masterfrom
perf/cuda-dense-q4k-batched-prefill-156

chore: remove stray review-agent diff artifacts

bbcc181
Select commit
Loading
Failed to load commit list.
GitGuardian / GitGuardian Security Checks succeeded Jun 6, 2026 in 1s

No secrets detected ✅

9 commits were scanned without uncovering any secrets.

Details

Commits scanned: 9

  • Pull request #161: perf/cuda-dense-q4k-batched-prefill-156 👉 master

🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.