{"id":23973375,"url":"https://github.com/tky823/bitlinear158compression","last_synced_at":"2026-06-12T06:31:36.427Z","repository":{"id":270443991,"uuid":"910389949","full_name":"tky823/BitLinear158Compression","owner":"tky823","description":"Compare compression models for inference by BitLinear158","archived":false,"fork":false,"pushed_at":"2025-01-04T06:26:40.000Z","size":33,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-24T15:56:59.204Z","etag":null,"topics":["cuda","pytorch","quantization"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tky823.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-12-31T06:30:21.000Z","updated_at":"2025-01-04T08:51:08.000Z","dependencies_parsed_at":"2024-12-31T08:18:50.763Z","dependency_job_id":"71cee1c7-6f6e-4479-b0db-227243ffe356","html_url":"https://github.com/tky823/BitLinear158Compression","commit_stats":null,"previous_names":["tky823/bitlinear158compression"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/tky823/BitLinear158Compression","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tky823%2FBitLinear158Compression","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tky823%2FBitLinear158Compression/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tky823%2FBitLinear158Compression/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tky823%2FBitLinear158Compression/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tky823","download_url":"https://codeload.github.com/tky823/BitLinear158Compression/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tky823%2FBitLinear158Compression/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34232789,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-12T02:00:06.859Z","response_time":109,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cuda","pytorch","quantization"],"created_at":"2025-01-07T04:57:51.047Z","updated_at":"2026-06-12T06:31:36.405Z","avatar_url":"https://github.com/tky823.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# BitLinear158Compression\n\nIn this library, we compare following compression models for inference by BitLinear158:\n\n- `BitLinear158`: Ternary weight is managed by `float32` (naive implementation)\n- `BitLinear158Int8Inference`: Ternary weight is managed by `int8`\n- `BitLinear158Uint2Inference`: Ternary weight is managed by `uint2` defined in `torchao`\n- `BitLinear158CppInference`: Ternary weight is managed by `int8` and forward pass is implemented by C++/CUDA. When weight is on CUDA, CUDA kernel is used under the hood.\n\n## Installation\n\n```sh\npip install .\n```\n\n## Test\n\n```sh\npython tests/test_bitlinear158_inference.py\n```\n\n## NOTE\nThere is room for improvement of computational speed by setting additional compling arguments in `setup.py`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftky823%2Fbitlinear158compression","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftky823%2Fbitlinear158compression","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftky823%2Fbitlinear158compression/lists"}