UPSTREAM PR #17072: [RFC] ggml: new backend for API Remoting #114
LOCI Review / Performance Review #114
succeeded
Nov 7, 2025 in 26m 56s
Performance varied across binaries, overall acceptable
0 binaries improved · 11 binaries unchanged · 5 binaries stable ~ within threshold · 0 binaries degraded ~ beyond threshold
| Binary | Δ % Response | Δ % Throughput | Performance (based on response time) |
|---|---|---|---|
build.bin.libggml-base.so |
0.00 | 0.00 | unchanged |
build.bin.libggml-cpu.so |
0.00 | 0.00 | unchanged |
build.bin.libggml.so |
0.00 | 0.00 | unchanged |
build.bin.libllama.so |
0.02 | -0.00 | stable |
build.bin.libmtmd.so |
0.00 | 0.00 | unchanged |
build.bin.llama-bench |
1.40 | -0.00 | stable |
build.bin.llama-cvector-generator |
0.02 | -0.00 | stable |
build.bin.llama-gemma3-cli |
0.00 | 0.00 | unchanged |
build.bin.llama-gguf-split |
0.00 | 0.00 | unchanged |
build.bin.llama-llava-cli |
0.00 | 0.00 | unchanged |
build.bin.llama-minicpmv-cli |
0.00 | 0.00 | unchanged |
build.bin.llama-quantize |
0.00 | 0.00 | unchanged |
build.bin.llama-qwen2vl-cli |
0.00 | 0.00 | unchanged |
build.bin.llama-run |
0.02 | -0.00 | stable |
build.bin.llama-tokenize |
0.00 | 0.00 | unchanged |
build.bin.llama-tts |
0.02 | -0.00 | stable |
Performance threshold: 30%
Default configuration used.
Note: Performance status is evaluated only from Δ% Response. Throughput is displayed for reference.
Access the complete analysis in the LOCI Dashboard.
Open the Pull Request linked to this check-run.
Loading