Skip to content

Conversation

@ggerganov
Copy link
Member

@ggerganov ggerganov commented Feb 4, 2026

Similar optimization as in #19281 to skip loading the all-zero mask blocks.

Model Test t/s master t/s gg/metal-fa-mask-zero-opt Speedup
qwen3moe 30B.A3B Q8_0 pp512 2177.84 2180.08 1.00
qwen3moe 30B.A3B Q8_0 pp8192 1731.35 1737.17 1.00
qwen3moe 30B.A3B Q8_0 pp16384 1232.67 1241.81 1.01
qwen3moe 30B.A3B Q8_0 pp32768 775.87 787.72 1.02
qwen3moe 30B.A3B Q8_0 pp65536 442.06 453.65 1.03

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants