Skip to content

ggml-quants: vectorize the per-block extremes scan in the reference quantizers - #43

Open
codspeed-hq[bot] wants to merge 1 commit into
masterfrom
codspeed-optim-vectorize-the-per-block-extremes-scan-in-the-refer-1785394478758
Open

ggml-quants: vectorize the per-block extremes scan in the reference quantizers#43
codspeed-hq[bot] wants to merge 1 commit into
masterfrom
codspeed-optim-vectorize-the-per-block-extremes-scan-in-the-refer-1785394478758

ggml-quants: vectorize the per-block extremes scan in the reference q…

15ee065
Select commit
Loading
Failed to load commit list.
CodSpeed HQ / CodSpeed Performance Analysis succeeded Jul 30, 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

⚡ 4 improved benchmarks
✅ 24 untouched benchmarks

Performance Changes

Mode Benchmark BASE HEAD Efficiency
Simulation quantize_chunk[q4_0] 246.7 µs 140.2 µs +75.95%
Simulation quantize_chunk[q4_1] 213.6 µs 144.8 µs +47.53%
Simulation quantize_chunk[q5_0] 386 µs 279.2 µs +38.25%
Simulation quantize_chunk[q8_0] 175 µs 135.6 µs +29.1%

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-vectorize-the-per-block-extremes-scan-in-the-refer-1785394478758 (15ee065) with master (46819c9)

Open in CodSpeed