René's URL Explorer Experiment


Title: GitHub - FasterDecoding/Medusa: Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Open Graph Title: GitHub - FasterDecoding/Medusa: Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

X Title: GitHub - FasterDecoding/Medusa: Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Description: Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads - FasterDecoding/Medusa

Open Graph Description: Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads - FasterDecoding/Medusa

X Description: Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads - FasterDecoding/Medusa

Opengraph URL: https://github.com/FasterDecoding/Medusa

X: @github

direct link

Domain: github.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:00a3e5f7-f9d3-b408-cd6e-877cb8b72c2d
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-idD23A:170B26:633596:7F091B:697DD255
html-safe-nonceec4a93763bb122fb17f5178c74cdea64e9e6068b3babb604bee20ca1cee29f3d
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJEMjNBOjE3MEIyNjo2MzM1OTY6N0YwOTFCOjY5N0REMjU1IiwidmlzaXRvcl9pZCI6Ijg2MTk1NDI1MDkxNzA1NzgwMDUiLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac92468b654e586a4daa60919cd6f1343567f63c94241ba975da0ffd3d1bc451fc
hovercard-subject-tagrepository:689541424
github-keyboard-shortcutsrepository,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location//
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/FasterDecoding/Medusa
twitter:imagehttps://opengraph.githubassets.com/a6e602585cc233d8ad13b942535cd9f2ddb6f00097dd720256ded28ef78a64dc/FasterDecoding/Medusa
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/a6e602585cc233d8ad13b942535cd9f2ddb6f00097dd720256ded28ef78a64dc/FasterDecoding/Medusa
og:image:altMedusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads - FasterDecoding/Medusa
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
None60279d4097367e16897439d16d6bbe4180663db828c666eeed2656988ffe59f6
turbo-cache-controlno-preview
go-importgithub.com/FasterDecoding/Medusa git https://github.com/FasterDecoding/Medusa.git
octolytics-dimension-user_id144572371
octolytics-dimension-user_loginFasterDecoding
octolytics-dimension-repository_id689541424
octolytics-dimension-repository_nwoFasterDecoding/Medusa
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id689541424
octolytics-dimension-repository_network_root_nwoFasterDecoding/Medusa
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
release7c85641c598ad130c74f7bcc27f58575cac69551
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://github.com/FasterDecoding/Medusa#start-of-content
https://github.com/
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FFasterDecoding%2FMedusa
GitHub CopilotWrite better code with AIhttps://github.com/features/copilot
GitHub SparkBuild and deploy intelligent appshttps://github.com/features/spark
GitHub ModelsManage and compare promptshttps://github.com/features/models
MCP RegistryNewIntegrate external toolshttps://github.com/mcp
ActionsAutomate any workflowhttps://github.com/features/actions
CodespacesInstant dev environmentshttps://github.com/features/codespaces
IssuesPlan and track workhttps://github.com/features/issues
Code ReviewManage code changeshttps://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilitieshttps://github.com/security/advanced-security
Code securitySecure your code as you buildhttps://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they starthttps://github.com/security/advanced-security/secret-protection
Why GitHubhttps://github.com/why-github
Documentationhttps://docs.github.com
Bloghttps://github.blog
Changeloghttps://github.blog/changelog
Marketplacehttps://github.com/marketplace
View all featureshttps://github.com/features
Enterpriseshttps://github.com/enterprise
Small and medium teamshttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
App Modernizationhttps://github.com/solutions/use-case/app-modernization
DevSecOpshttps://github.com/solutions/use-case/devsecops
DevOpshttps://github.com/solutions/use-case/devops
CI/CDhttps://github.com/solutions/use-case/ci-cd
View all use caseshttps://github.com/solutions/use-case
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
View all industrieshttps://github.com/solutions/industry
View all solutionshttps://github.com/solutions
AIhttps://github.com/resources/articles?topic=ai
Software Developmenthttps://github.com/resources/articles?topic=software-development
DevOpshttps://github.com/resources/articles?topic=devops
Securityhttps://github.com/resources/articles?topic=security
View all topicshttps://github.com/resources/articles
Customer storieshttps://github.com/customer-stories
Events & webinarshttps://github.com/resources/events
Ebooks & reportshttps://github.com/resources/whitepapers
Business insightshttps://github.com/solutions/executive-insights
GitHub Skillshttps://skills.github.com
Documentationhttps://docs.github.com
Customer supporthttps://support.github.com
Community forumhttps://github.com/orgs/community/discussions
Trust centerhttps://github.com/trust-center
Partnershttps://github.com/partners
GitHub SponsorsFund open source developershttps://github.com/sponsors
Security Labhttps://securitylab.github.com
Maintainer Communityhttps://maintainers.github.com
Acceleratorhttps://github.com/accelerator
Archive Programhttps://archiveprogram.github.com
Topicshttps://github.com/topics
Trendinghttps://github.com/trending
Collectionshttps://github.com/collections
Enterprise platformAI-powered developer platformhttps://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security featureshttps://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/premium-support
Pricinghttps://github.com/pricing
Search syntax tipshttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentationhttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2FFasterDecoding%2FMedusa
Sign up https://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=FasterDecoding%2FMedusa
Reloadhttps://github.com/FasterDecoding/Medusa
Reloadhttps://github.com/FasterDecoding/Medusa
Reloadhttps://github.com/FasterDecoding/Medusa
FasterDecoding https://github.com/FasterDecoding
Medusahttps://github.com/FasterDecoding/Medusa
Notifications https://github.com/login?return_to=%2FFasterDecoding%2FMedusa
Fork 193 https://github.com/login?return_to=%2FFasterDecoding%2FMedusa
Star 2.7k https://github.com/login?return_to=%2FFasterDecoding%2FMedusa
sites.google.com/view/medusa-llmhttps://sites.google.com/view/medusa-llm
Apache-2.0 license https://github.com/FasterDecoding/Medusa/blob/main/LICENSE
2.7k stars https://github.com/FasterDecoding/Medusa/stargazers
193 forks https://github.com/FasterDecoding/Medusa/forks
Branches https://github.com/FasterDecoding/Medusa/branches
Tags https://github.com/FasterDecoding/Medusa/tags
Activity https://github.com/FasterDecoding/Medusa/activity
Star https://github.com/login?return_to=%2FFasterDecoding%2FMedusa
Notifications https://github.com/login?return_to=%2FFasterDecoding%2FMedusa
Code https://github.com/FasterDecoding/Medusa
Issues 51 https://github.com/FasterDecoding/Medusa/issues
Pull requests 6 https://github.com/FasterDecoding/Medusa/pulls
Discussions https://github.com/FasterDecoding/Medusa/discussions
Actions https://github.com/FasterDecoding/Medusa/actions
Projects 0 https://github.com/FasterDecoding/Medusa/projects
Security 0 https://github.com/FasterDecoding/Medusa/security
Insights https://github.com/FasterDecoding/Medusa/pulse
Code https://github.com/FasterDecoding/Medusa
Issues https://github.com/FasterDecoding/Medusa/issues
Pull requests https://github.com/FasterDecoding/Medusa/pulls
Discussions https://github.com/FasterDecoding/Medusa/discussions
Actions https://github.com/FasterDecoding/Medusa/actions
Projects https://github.com/FasterDecoding/Medusa/projects
Security https://github.com/FasterDecoding/Medusa/security
Insights https://github.com/FasterDecoding/Medusa/pulse
Brancheshttps://github.com/FasterDecoding/Medusa/branches
Tagshttps://github.com/FasterDecoding/Medusa/tags
https://github.com/FasterDecoding/Medusa/branches
https://github.com/FasterDecoding/Medusa/tags
72 Commitshttps://github.com/FasterDecoding/Medusa/commits/main/
https://github.com/FasterDecoding/Medusa/commits/main/
assetshttps://github.com/FasterDecoding/Medusa/tree/main/assets
assetshttps://github.com/FasterDecoding/Medusa/tree/main/assets
data_generationhttps://github.com/FasterDecoding/Medusa/tree/main/data_generation
data_generationhttps://github.com/FasterDecoding/Medusa/tree/main/data_generation
llm_judgehttps://github.com/FasterDecoding/Medusa/tree/main/llm_judge
llm_judgehttps://github.com/FasterDecoding/Medusa/tree/main/llm_judge
medusahttps://github.com/FasterDecoding/Medusa/tree/main/medusa
medusahttps://github.com/FasterDecoding/Medusa/tree/main/medusa
notebookshttps://github.com/FasterDecoding/Medusa/tree/main/notebooks
notebookshttps://github.com/FasterDecoding/Medusa/tree/main/notebooks
scriptshttps://github.com/FasterDecoding/Medusa/tree/main/scripts
scriptshttps://github.com/FasterDecoding/Medusa/tree/main/scripts
.gitignorehttps://github.com/FasterDecoding/Medusa/blob/main/.gitignore
.gitignorehttps://github.com/FasterDecoding/Medusa/blob/main/.gitignore
CITATION.cffhttps://github.com/FasterDecoding/Medusa/blob/main/CITATION.cff
CITATION.cffhttps://github.com/FasterDecoding/Medusa/blob/main/CITATION.cff
LICENSEhttps://github.com/FasterDecoding/Medusa/blob/main/LICENSE
LICENSEhttps://github.com/FasterDecoding/Medusa/blob/main/LICENSE
README.mdhttps://github.com/FasterDecoding/Medusa/blob/main/README.md
README.mdhttps://github.com/FasterDecoding/Medusa/blob/main/README.md
ROADMAP.mdhttps://github.com/FasterDecoding/Medusa/blob/main/ROADMAP.md
ROADMAP.mdhttps://github.com/FasterDecoding/Medusa/blob/main/ROADMAP.md
create_data.pyhttps://github.com/FasterDecoding/Medusa/blob/main/create_data.py
create_data.pyhttps://github.com/FasterDecoding/Medusa/blob/main/create_data.py
deepspeed.jsonhttps://github.com/FasterDecoding/Medusa/blob/main/deepspeed.json
deepspeed.jsonhttps://github.com/FasterDecoding/Medusa/blob/main/deepspeed.json
pyproject.tomlhttps://github.com/FasterDecoding/Medusa/blob/main/pyproject.toml
pyproject.tomlhttps://github.com/FasterDecoding/Medusa/blob/main/pyproject.toml
simple_gradio_interface.pyhttps://github.com/FasterDecoding/Medusa/blob/main/simple_gradio_interface.py
simple_gradio_interface.pyhttps://github.com/FasterDecoding/Medusa/blob/main/simple_gradio_interface.py
READMEhttps://github.com/FasterDecoding/Medusa
Apache-2.0 licensehttps://github.com/FasterDecoding/Medusa
https://github.com/FasterDecoding/Medusa/blob/main/assets/logo.png
https://github.com/FasterDecoding/Medusa#medusa-simple-framework-for-accelerating-llm-generation-with-multiple-decoding-heads
Bloghttps://sites.google.com/view/medusa-llm
Reporthttps://arxiv.org/abs/2401.10774
Roadmaphttps://github.com/FasterDecoding/Medusa/blob/main/ROADMAP.md
arXivhttps://arxiv.org/abs/2401.10774
https://github.com/FasterDecoding/Medusa#introduction
https://github.com/FasterDecoding/Medusa#contents
Introductionhttps://github.com/FasterDecoding/Medusa#introduction
Contentshttps://github.com/FasterDecoding/Medusa#contents
Installationhttps://github.com/FasterDecoding/Medusa#installation
Method 1: With pip (may not be the latest version)https://github.com/FasterDecoding/Medusa#method-1-with-pip-may-not-be-the-latest-version
Method 2: From the source (recommended)https://github.com/FasterDecoding/Medusa#method-2-from-the-source-recommended
Model Weightshttps://github.com/FasterDecoding/Medusa#model-weights
Inferencehttps://github.com/FasterDecoding/Medusa#inference
Traininghttps://github.com/FasterDecoding/Medusa#training
Training (legacy)https://github.com/FasterDecoding/Medusa#training-legacy
Push to Hugging Face Hubhttps://github.com/FasterDecoding/Medusa#push-to-hugging-face-hub
Citationhttps://github.com/FasterDecoding/Medusa#citation
Codebase Guidehttps://github.com/FasterDecoding/Medusa#codebase-guide
Community Adoptionhttps://github.com/FasterDecoding/Medusa#community-adoption
Contributinghttps://github.com/FasterDecoding/Medusa#contributing
Acknowledgementshttps://github.com/FasterDecoding/Medusa#acknowledgements
https://github.com/FasterDecoding/Medusa#installation
https://github.com/FasterDecoding/Medusa#method-1-with-pip-may-not-be-the-latest-version
https://github.com/FasterDecoding/Medusa#method-2-from-the-source-recommended
https://github.com/FasterDecoding/Medusa#model-weights
https://github.com/FasterDecoding/Medusa#medusa-1
FasterDecoding/medusa-vicuna-7b-v1.3https://huggingface.co/FasterDecoding/medusa-vicuna-7b-v1.3
FasterDecoding/medusa-vicuna-13b-v1.3https://huggingface.co/FasterDecoding/medusa-vicuna-13b-v1.3
FasterDecoding/medusa-vicuna-33b-v1.3https://huggingface.co/FasterDecoding/medusa-vicuna-33b-v1.3
https://github.com/FasterDecoding/Medusa#medusa-2
FasterDecoding/medusa-1.0-zephyr-7b-betahttps://huggingface.co/FasterDecoding/medusa-1.0-zephyr-7b-beta
FasterDecoding/medusa-1.0-vicuna-7b-v1.5https://huggingface.co/FasterDecoding/medusa-1.0-vicuna-7b-v1.5
FasterDecoding/medusa-1.0-vicuna-13b-v1.5https://huggingface.co/FasterDecoding/medusa-1.0-vicuna-13b-v1.5
FasterDecoding/medusa-1.0-vicuna-33b-v1.5https://huggingface.co/FasterDecoding/medusa-1.0-vicuna-33b-v1.5
https://github.com/FasterDecoding/Medusa#inference
https://github.com/FasterDecoding/Medusa#training
axolotlhttps://github.com/OpenAccess-AI-Collective/axolotl
forkhttps://github.com/ctlllll/axolotl
src/axolotl/utils/models.pyhttps://github.com/ctlllll/axolotl/blob/main/src/axolotl/utils/models.py
examples/medusahttps://github.com/ctlllll/axolotl/tree/main/examples/medusa
data_generation folderhttps://github.com/FasterDecoding/Medusa/blob/main/data_generation
https://github.com/FasterDecoding/Medusa#training-on-various-architectures
https://github.com/FasterDecoding/Medusa#prepare-the-data
https://github.com/FasterDecoding/Medusa#adapt-the-data-to-the-model-you-want-to-enable-medusa-on
mistralai/Mistral-7B-Instruct-v0.2https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2
text-generation-inferencehttps://github.com/huggingface/text-generation-inference
speed up inferencehttps://huggingface.co/docs/text-generation-inference/index
https://github.com/FasterDecoding/Medusa#train-the-model
FastChathttps://github.com/lm-sys/FastChat#fine-tuning
https://github.com/FasterDecoding/Medusa#push-to-hugging-face-hub
https://github.com/FasterDecoding/Medusa#citation
https://github.com/FasterDecoding/Medusa#codebase-guide
https://github.com/FasterDecoding/Medusa#community-adoption
TensorRT-LLMhttps://github.com/NVIDIA/TensorRT-LLM/tree/main/examples/medusa
TGIhttps://github.com/huggingface/text-generation-inference/blob/main/server/text_generation_server/utils/medusa.py
RTP-LLMhttps://github.com/alibaba/rtp-llm/blob/main/docs/SpeculativeDecoding-Tutroial.md#medusa-decoding
https://github.com/FasterDecoding/Medusa#contributing
Roadmaphttps://github.com/FasterDecoding/Medusa/blob/main/ROADMAP.md
https://github.com/FasterDecoding/Medusa#acknowledgements
FastChathttps://github.com/lm-sys/FastChat
TinyChathttps://github.com/mit-han-lab/llm-awq/tree/main/
vllmhttps://github.com/vllm-project/vllm
axolotlhttps://github.com/OpenAccess-AI-Collective/axolotl
Together AIhttps://together.ai/
MyShell AIhttps://myshell.ai/
Chai AIhttps://www.chai-research.com/
sites.google.com/view/medusa-llmhttps://sites.google.com/view/medusa-llm
llm https://github.com/topics/llm
llm-inference https://github.com/topics/llm-inference
Readme https://github.com/FasterDecoding/Medusa#readme-ov-file
Apache-2.0 license https://github.com/FasterDecoding/Medusa#Apache-2.0-1-ov-file
Please reload this pagehttps://github.com/FasterDecoding/Medusa
Activityhttps://github.com/FasterDecoding/Medusa/activity
Custom propertieshttps://github.com/FasterDecoding/Medusa/custom-properties
2.7k starshttps://github.com/FasterDecoding/Medusa/stargazers
28 watchinghttps://github.com/FasterDecoding/Medusa/watchers
193 forkshttps://github.com/FasterDecoding/Medusa/forks
Report repository https://github.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2FFasterDecoding%2FMedusa&report=FasterDecoding+%28user%29
Releases 1https://github.com/FasterDecoding/Medusa/releases
Medusa-v0.1 Latest Sep 11, 2023 https://github.com/FasterDecoding/Medusa/releases/tag/v0.1
Packages 0https://github.com/orgs/FasterDecoding/packages?repo_name=Medusa
Please reload this pagehttps://github.com/FasterDecoding/Medusa
Contributors 10https://github.com/FasterDecoding/Medusa/graphs/contributors
https://github.com/leeyeehoo
https://github.com/ctlllll
https://github.com/Narsil
https://github.com/harveyp123
https://github.com/Btlmd
https://github.com/Mrw33554432
https://github.com/eltociear
https://github.com/zhyncs
https://github.com/rajveer43
https://github.com/kalomaze
Jupyter Notebook 65.5% https://github.com/FasterDecoding/Medusa/search?l=jupyter-notebook
Python 34.4% https://github.com/FasterDecoding/Medusa/search?l=python
Shell 0.1% https://github.com/FasterDecoding/Medusa/search?l=shell
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.