UPSTREAM PR #17937: common : refactor common_sampler + grammar logic changes #523
LOCI Review / Performance Review #523
succeeded
Dec 11, 2025 in 33m 19s
Performance varied across binaries, overall acceptable
1 binary improved · 9 binaries unchanged · 6 binaries stable ~ within threshold · 0 binaries degraded ~ beyond threshold
| Binary | Δ % Response | Δ % Throughput | Performance (based on response time) |
|---|---|---|---|
build.bin.libggml-base.so |
0 | 0 | unchanged |
build.bin.libggml-cpu.so |
0 | 0 | unchanged |
build.bin.libggml.so |
0 | 0 | unchanged |
build.bin.libllama.so |
0 | 0 | unchanged |
build.bin.libmtmd.so |
0 | 0 | unchanged |
build.bin.llama-bench |
5.23 | 1.64 | stable |
build.bin.llama-cvector-generator |
-0.17 | 0.25 | improved |
build.bin.llama-gemma3-cli |
0 | 0 | unchanged |
build.bin.llama-gguf-split |
11.6 | 2.43 | stable |
build.bin.llama-llava-cli |
0 | 0 | unchanged |
build.bin.llama-minicpmv-cli |
0 | 0 | unchanged |
build.bin.llama-quantize |
10.6 | 2.35 | stable |
build.bin.llama-qwen2vl-cli |
0 | 0 | unchanged |
build.bin.llama-run |
0.2 | 0.39 | stable |
build.bin.llama-tokenize |
11.73 | 2.42 | stable |
build.bin.llama-tts |
0.3 | 0.2 | stable |
Performance threshold: 30%
Default configuration used.
Note: Performance status is evaluated only from Δ% Response. Throughput is displayed for reference.
Explore the complete analysis inside the Version Insights.
Loading