popov/neuron-tai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: compare safetensors and gguf on cpu and gpu

Browse Source
This commit is contained in:
Dobromir Popov
2026-07-14 18:45:12 +03:00
parent c7554ef7d8
commit 5b33bf8b99
5 changed files with 88 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
tests/test_performance_contract.py
View File

@@ -20,9 +20,14 @@ def test_default_contract_is_architecture_aligned_and_small():
"name": "DeepSeek-V2-Lite-Chat",
"architecture": "deepseek2",
"safetensors_repo": "deepseek-ai/DeepSeek-V2-Lite-Chat",
"safetensors_precision": "bfloat16",
"gguf_repo": "second-state/DeepSeek-V2-Lite-Chat-GGUF",
"gguf_quant": "Q2_K",
"gguf_size_gb": 6.43,
"comparison_policy": (
"same model/revision, closest practical low-footprint precision pair: "
"BF16 safetensors versus Q2_K GGUF"
),
"rationale": (
"Smallest DeepSeek-family benchmark anchor that still points toward "
"DeepSeek-V4-Flash; keeps the runtime on the DeepSeek2 path instead "
@@ -31,14 +36,30 @@ def test_default_contract_is_architecture_aligned_and_small():
}
assert payload["benchmark_lanes"] == [
{
"id": "transformers-safetensors",
"id": "transformers-safetensors-cpu",
"runtime": "transformers",
"device": "cpu",
"recipe": "current safetensors recipe",
"concurrency_levels": [1, 4],
},
{
"id": "llama-cpp-gguf",
"id": "llama-cpp-gguf-cpu",
"runtime": "llama.cpp",
"device": "cpu",
"recipe": "whole-model GGUF recipe",
"concurrency_levels": [1, 4],
},
{
"id": "transformers-safetensors-gpu",
"runtime": "transformers",
"device": "gpu",
"recipe": "current safetensors recipe",
"concurrency_levels": [1, 4],
},
{
"id": "llama-cpp-gguf-gpu",
"runtime": "llama.cpp",
"device": "gpu",
"recipe": "whole-model GGUF recipe",
"concurrency_levels": [1, 4],
},