Skip to content

perf(gemma4-cuda): MMQ + flash-attention prefill + dp4a decode (#141/#142)#143

Merged
pekkah merged 12 commits into
masterfrom
perf/gemma4-cuda-prefill-gemm-decode-dp4a-141-142
Jun 6, 2026
Merged

perf(gemma4-cuda): MMQ + flash-attention prefill + dp4a decode (#141/#142)#143
pekkah merged 12 commits into
masterfrom
perf/gemma4-cuda-prefill-gemm-decode-dp4a-141-142

docs(readme): Gemma 4 CUDA prefill 1564→2853 (MMQ + flash attn + batc…

494af75
Select commit
Loading
Failed to load commit list.
GitGuardian / GitGuardian Security Checks succeeded Jun 5, 2026 in 1s

No secrets detected ✅

12 commits were scanned without uncovering any secrets.

Details

Commits scanned: 12

  • Pull request #143: perf/gemma4-cuda-prefill-gemm-decode-dp4a-141-142 👉 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.