awesome-llama: https://github.com/vectorch-ai/ScaleLLM
cuda efficiency gpu inference llama llama3 llm llm-inference model performance production serving speculative transformer
Score: 11.746510315701725
Last synced: about 3 hours ago
JSON representation
Repository metadata:
A high-performance inference system for large language models, designed for production environments.
- Host: GitHub
- URL: https://github.com/vectorch-ai/ScaleLLM
- Owner: vectorch-ai
- License: apache-2.0
- Archived: true
- Created: 2023-07-24T20:14:28.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2025-12-19T04:19:34.000Z (10 months ago)
- Last Synced: 2026-10-25T07:14:02.580Z (2 days ago)
- Topics: cuda, efficiency, gpu, inference, llama, llama3, llm, llm-inference, model, performance, production, serving, speculative, transformer
- Language: C++
- Homepage: https://docs.vectorch.com/
- Size: 19.8 MB
- Stars: 498
- Watchers: 17
- Forks: 41
- Open Issues: 56
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Owner metadata:
- Name: Vectorch AI
- Login: vectorch-ai
- Email: info@vectorch.com
- Kind: organization
- Description: Empowering Teams to Unleash Discoverability
- Website: http://www.vectorch.com
- Location: United States of America
- Twitter:
- Company:
- Icon url: https://avatars.githubusercontent.com/u/136120791?v=4
- Repositories: 19
- Last Synced at: 2026-10-25T07:25:30.754Z
- Profile URL: https://github.com/vectorch-ai
GitHub Events
Total
- Create event: 123
- Delete event: 100
- Fork event: 10
- Issue comment event: 4
- Issues event: 18
- Pull request event: 233
- Pull request review event: 4
- Push event: 424
- Release event: 4
- Watch event: 85
- Total: 1005
Last Year
- Fork event: 1
- Push event: 5
- Watch event: 7
- Total: 13
Committers metadata
Last synced: 1 day ago
Total Commits: 772
Total Committers: 6
Avg Commits per committer: 128.667
Development Distribution Score (DDS): 0.038
Commits in past year: 3
Committers in past year: 1
Avg Commits per committer in past year: 3.0
Development Distribution Score (DDS) in past year: 0.0
| Name | Commits | |
|---|---|---|
| Michael Mi | g****i@g****m | 743 |
| Tongxuan Liu | t****x@m****n | 22 |
| Xiao Liang | s****n@g****m | 4 |
| xianzhedong | 8****e | 1 |
| panhengyu | 4****5 | 1 |
| Kevin Li | k****5@g****m | 1 |
Issue and Pull Request metadata
Last synced: 1 day ago
Total issues: 88
Total pull requests: 609
Average time to close issues: 26 days
Average time to close pull requests: 1 day
Total issue authors: 27
Total pull request authors: 6
Average comments per issue: 1.27
Average comments per pull request: 0.04
Merged pull request: 505
Bot issues: 0
Bot pull requests: 0
Past year issues: 1
Past year pull requests: 1
Past year average time to close issues: 13 days
Past year average time to close pull requests: about 2 hours
Past year issue authors: 1
Past year pull request authors: 1
Past year average comments per issue: 0.0
Past year average comments per pull request: 0.0
Past year merged pull request: 1
Past year bot issues: 0
Past year bot pull requests: 0
Top Issue Authors
- guocuimi (53)
- liutongxuan (6)
- sitabulaixizawaluduo (2)
- tp-nan (2)
- BUJIDAOVS (2)
- Arcmoon-Hu (2)
- WangErXiao (1)
- zyxcambridge (1)
- omarmhaimdat (1)
- spongxin (1)
- goldenquant (1)
- Siegi96 (1)
- latheesan-k (1)
- kitckso (1)
- dengyingxu (1)
Top Pull Request Authors
- guocuimi (569)
- liutongxuan (23)
- dongxianzhe (11)
- 936187425 (3)
- ShijiaTang (2)
- Argannor (1)
Top Issue Labels
- enhancement (8)
- good first issue (6)
- bug (5)
- investigation needed (3)
- backlog (1)
- duplicate (1)
Top Pull Request Labels
Package metadata
- Total packages: 1
-
Total downloads:
- pypi: 37 last-month
- Total dependent packages: 0
- Total dependent repositories: 0
- Total versions: 19
- Total maintainers: 1
pypi.org: scalellm
A high-performance inference system for large language models.
- Homepage: https://github.com/vectorch-ai/ScaleLLM
- Documentation: https://scalellm.readthedocs.io/
- Licenses: Apache 2.0
- Latest release: 0.2.6 (published about 1 year ago)
- Last Synced: 2026-10-26T10:32:42.525Z (1 day ago)
- Versions: 19
- Dependent Packages: 0
- Dependent Repositories: 0
- Downloads: 37 Last month
-
Rankings:
- Dependent packages count: 10.965%
- Average: 36.354%
- Dependent repos count: 61.743%
- Maintainers (1)
Dependencies
- actions/cache v3 composite
- actions/checkout v3 composite
- golang 1.21-alpine build
- huggingface_hub *
- abseil >=20230125.3
- benchmark >=1.8.0
- glog >=0.6.0#2
- gtest >=1.13.0
- sentencepiece >=0.1.97
- github.com/golang/glog v1.1.0
- github.com/golang/protobuf v1.5.3
- github.com/grpc-ecosystem/grpc-gateway/v2 v2.17.1
- golang.org/x/net v0.14.0
- golang.org/x/sys v0.11.0
- golang.org/x/text v0.12.0
- google.golang.org/genproto v0.0.0-20230803162519-f966b187b2e5
- google.golang.org/genproto/googleapis/api v0.0.0-20230822172742-b8732ec3820d
- google.golang.org/genproto/googleapis/rpc v0.0.0-20230822172742-b8732ec3820d
- google.golang.org/grpc v1.57.0
- google.golang.org/protobuf v1.31.0
- github.com/golang/glog v1.1.0
- github.com/golang/protobuf v1.5.0
- github.com/golang/protobuf v1.5.3
- github.com/google/go-cmp v0.5.5
- github.com/google/go-cmp v0.5.9
- github.com/grpc-ecosystem/grpc-gateway/v2 v2.17.1
- golang.org/x/net v0.14.0
- golang.org/x/sys v0.11.0
- golang.org/x/text v0.12.0
- golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543
- google.golang.org/genproto v0.0.0-20230803162519-f966b187b2e5
- google.golang.org/genproto/googleapis/api v0.0.0-20230822172742-b8732ec3820d
- google.golang.org/genproto/googleapis/rpc v0.0.0-20230822172742-b8732ec3820d
- google.golang.org/grpc v1.57.0
- google.golang.org/protobuf v1.26.0-rc.1
- google.golang.org/protobuf v1.26.0
- google.golang.org/protobuf v1.31.0
- ${BASE_IMAGE} latest build
- grafana/grafana latest
- prom/prometheus latest
- ${BASE_IMAGE} latest build
- actions/checkout v4 composite
- actions/download-artifact v4 composite
- actions/upload-artifact v4 composite
- pypa/gh-action-pypi-publish release/v1.12 composite
- furo ==2024.5.6
- myst-parser ==3.0.1
- sphinx ==7.3.7
- sphinx-autobuild *
- sphinx-copybutton ==0.5.2
- sphinx-reredirects ==0.1.3
- sphinx-tabs ==3.4.5
- sphinx-toolbox ==3.5.0
- sphinxcontrib-httpdomain ==1.8.1
- sphinxcontrib-napoleon ==0.7
- jinja2 * development
- pytest * development
- setuptools * development
- triton >=3.2.0 development
- wheel * development
- actions/checkout v4 composite
- actions/download-artifact v4 composite
- actions/upload-artifact v4 composite
- actions/checkout v4 composite
- actions/download-artifact v4 composite
- actions/upload-artifact v4 composite
- softprops/action-gh-release v2 composite
- actions/checkout v4 composite
- actions/setup-python v5 composite
- actions/checkout v4 composite
- actions/download-artifact v4 composite
- actions/upload-artifact v4 composite
- actions/checkout v4 composite
- docker/build-push-action v5 composite
- docker/login-action v3 composite
- docker/setup-buildx-action v3 composite
- docker/setup-qemu-action v3 composite
- actions/checkout v4 composite
- actions/configure-pages v5 composite
- actions/deploy-pages v4 composite
- actions/upload-pages-artifact v3 composite
- actions/checkout v4 composite
- docker/build-push-action v5 composite
- docker/login-action v3 composite
- docker/setup-buildx-action v3 composite
- docker/setup-qemu-action v3 composite
- actions/checkout v4 composite
- docker/build-push-action v5 composite
- docker/login-action v3 composite
- docker/setup-buildx-action v3 composite
- docker/setup-qemu-action v3 composite
- accelerate ==1.10.1 test
- anyio ==4.10.0 test
- httpx ==0.27.2 test
- openai ==1.107.2 test
- pytest ==8.4.2 test
- pytest-asyncio ==1.2.0 test
- pytest-forked ==1.6.0 test
- pytest-rerunfailures ==16.0.1 test
- pytest-shard ==0.1.2 test
- requests ==2.32.5 test
- six ==1.17.0 test
- transformers ==4.56.1 test