Skip to content

ggml-cpu: 2x2 register-blocked AVX2 kernel for ggml_vec_dot_q4_0_q8_0 - #39

Open
codspeed-hq[bot] wants to merge 1 commit into
masterfrom
codspeed-optim-2-2-register-blocked-avx2-kernel-for-ggml-vec-dot-1785326413536
Open

ggml-cpu: 2x2 register-blocked AVX2 kernel for ggml_vec_dot_q4_0_q8_0#39
codspeed-hq[bot] wants to merge 1 commit into
masterfrom
codspeed-optim-2-2-register-blocked-avx2-kernel-for-ggml-vec-dot-1785326413536

ggml-cpu: 2x2 register-blocked AVX2 kernel for ggml_vec_dot_q4_0_q8_0

418d842
Select commit
Loading
Failed to load commit list.
CodSpeed HQ / CodSpeed Performance Analysis succeeded Jul 29, 2026 in 0s

Performance Gate Passed

⚠️ Different runtime environments detected

Some benchmarks with significant performance changes were compared across different runtime environments,
which may affect the accuracy of the results.

Open the report in CodSpeed to investigate

⚡ 1 improved benchmark
✅ 27 untouched benchmarks

Performance Changes

Mode Benchmark BASE HEAD Efficiency
Simulation mul_mat[q4_0] 102 ms 65.7 ms +55.13%

Tip

Curious why this is faster? Comment @codspeedbot explain why this is faster on this PR, or directly use the CodSpeed MCP with your agent.


Comparing codspeed-optim-2-2-register-blocked-avx2-kernel-for-ggml-vec-dot-1785326413536 (418d842) with master (46819c9)

Open in CodSpeed