inferencebench-code 0.0.2__tar.gz → 0.1.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/.gitignore +6 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/PKG-INFO +1 -1
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/pyproject.toml +1 -1
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/README.md +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/__init__.py +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/benchmarks/humaneval-mini.yaml +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/benchmarks/mbpp-mini.yaml +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/datasets/humaneval-mini.jsonl +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/datasets/mbpp-mini.jsonl +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/plugin.py +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/py.typed +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/runner.py +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/schemas.py +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/src/inferencebench_code/scoring.py +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/tests/conftest.py +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/tests/test_code_plugin.py +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/tests/test_code_runner.py +0 -0
- {inferencebench_code-0.0.2 → inferencebench_code-0.1.0}/tests/test_code_scoring.py +0 -0
|
@@ -104,6 +104,12 @@ validation-runs/2026-05-18-multi-vendor-marathon/marathon/*
|
|
|
104
104
|
!validation-runs/2026-05-25-voice-rtx4000ada/*.json
|
|
105
105
|
!validation-runs/2026-05-29-voice-testbm-h100
|
|
106
106
|
!validation-runs/2026-05-29-voice-testbm-h100/*.json
|
|
107
|
+
# LLM inference validation envelopes (Qwen2.5-72B-Instruct on 4xH100, TP=4, BF16)
|
|
108
|
+
!validation-runs/2026-06-13-llm-h100
|
|
109
|
+
!validation-runs/2026-06-13-llm-h100/*.json
|
|
110
|
+
# Multi-modality validation envelopes (mt + code + vision + embeddings on H100)
|
|
111
|
+
!validation-runs/2026-06-13-multi-modality-h100
|
|
112
|
+
!validation-runs/2026-06-13-multi-modality-h100/*.json
|
|
107
113
|
|
|
108
114
|
# Model weights / datasets (use Git LFS or S3)
|
|
109
115
|
*.bin
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: inferencebench-code
|
|
3
|
-
Version: 0.0
|
|
3
|
+
Version: 0.1.0
|
|
4
4
|
Summary: Code-generation plugin for InferenceBench Suite (HumanEval-style execution-based scoring).
|
|
5
5
|
Project-URL: Homepage, https://github.com/yobitelcomm/bench
|
|
6
6
|
Author-email: Yobitel Communications <bench@yobitel.com>
|
|
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "inferencebench-code"
|
|
7
|
-
version = "0.0
|
|
7
|
+
version = "0.1.0"
|
|
8
8
|
description = "Code-generation plugin for InferenceBench Suite (HumanEval-style execution-based scoring)."
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
requires-python = ">=3.12"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|