René's URL Explorer Experiment


Title: GitHub - Infini-AI-Lab/MagicDec: [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding

Open Graph Title: GitHub - Infini-AI-Lab/MagicDec: [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding

X Title: GitHub - Infini-AI-Lab/MagicDec: [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding

Description: [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding - Infini-AI-Lab/MagicDec

Open Graph Description: [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding - Infini-AI-Lab/MagicDec

X Description: [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding - Infini-AI-Lab/MagicDec

Opengraph URL: https://github.com/Infini-AI-Lab/MagicDec

X: @github

direct link

Domain: patch-diff.githubusercontent.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:c2c492bc-d853-4659-02b7-8a6dbf9398a0
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-idD088:7DFC8:812450C:AE95D39:698CFFCC
html-safe-nonce7f066889acb6e5ff62fd3360000b7283253683b6dcfbf6de4a02b64a4d2cfc3f
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJEMDg4OjdERkM4OjgxMjQ1MEM6QUU5NUQzOTo2OThDRkZDQyIsInZpc2l0b3JfaWQiOiI0ODI0MTE3OTM2MDk0NTc2MTIiLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac1608eac3b03e415a2ba68be9131a3dd857b762eaa4fcf415a501d12c2d394000
hovercard-subject-tagrepository:838474043
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/Infini-AI-Lab/MagicDec
twitter:imagehttps://opengraph.githubassets.com/d9ceaa3b1606ee2ecb54e59e5b8ae63a90da4a47796f829b6ba2b03c9d741b2a/Infini-AI-Lab/MagicDec
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/d9ceaa3b1606ee2ecb54e59e5b8ae63a90da4a47796f829b6ba2b03c9d741b2a/Infini-AI-Lab/MagicDec
og:image:alt[ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding - Infini-AI-Lab/MagicDec
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
Nonef2da95634bce8a94cfa4123788169bfabdf845fd1d790fbaaaaab09dcfebdf28
turbo-cache-controlno-preview
go-importgithub.com/Infini-AI-Lab/MagicDec git https://github.com/Infini-AI-Lab/MagicDec.git
octolytics-dimension-user_id149595684
octolytics-dimension-user_loginInfini-AI-Lab
octolytics-dimension-repository_id838474043
octolytics-dimension-repository_nwoInfini-AI-Lab/MagicDec
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forkfalse
octolytics-dimension-repository_network_root_id838474043
octolytics-dimension-repository_network_root_nwoInfini-AI-Lab/MagicDec
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
releasec21843b18feba17d11efb1895a7db61e8672f2cf
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#start-of-content
https://patch-diff.githubusercontent.com/
Sign in https://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FInfini-AI-Lab%2FMagicDec
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://patch-diff.githubusercontent.com/login?return_to=https%3A%2F%2Fgithub.com%2FInfini-AI-Lab%2FMagicDec
Sign up https://patch-diff.githubusercontent.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=Infini-AI-Lab%2FMagicDec
Reloadhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Reloadhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Reloadhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Infini-AI-Lab https://patch-diff.githubusercontent.com/Infini-AI-Lab
MagicDechttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FInfini-AI-Lab%2FMagicDec
Fork 9 https://patch-diff.githubusercontent.com/login?return_to=%2FInfini-AI-Lab%2FMagicDec
Star 142 https://patch-diff.githubusercontent.com/login?return_to=%2FInfini-AI-Lab%2FMagicDec
Apache-2.0 license https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/LICENSE
142 stars https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/stargazers
9 forks https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/forks
Branches https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/branches
Tags https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tags
Activity https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/activity
Star https://patch-diff.githubusercontent.com/login?return_to=%2FInfini-AI-Lab%2FMagicDec
Notifications https://patch-diff.githubusercontent.com/login?return_to=%2FInfini-AI-Lab%2FMagicDec
Code https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Issues 8 https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/issues
Pull requests 0 https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/pulls
Actions https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/actions
Projects 0 https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/projects
Security 0 https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/security
Insights https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/pulse
Code https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Issues https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/issues
Pull requests https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/pulls
Actions https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/actions
Projects https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/projects
Security https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/security
Insights https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/pulse
Brancheshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/branches
Tagshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tags
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/branches
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tags
102 Commitshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/commits/main/
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/commits/main/
Datahttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/Data
Datahttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/Data
Enginehttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/Engine
Enginehttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/Engine
pageshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/pages
pageshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/pages
statichttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/static
statichttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/static
testshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/tests
testshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/tree/main/tests
.gitignorehttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/.gitignore
.gitignorehttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/.gitignore
LICENSEhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/LICENSE
LICENSEhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/LICENSE
README.mdhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/README.md
README.mdhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/README.md
convert_hf_checkpoint.pyhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/convert_hf_checkpoint.py
convert_hf_checkpoint.pyhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/convert_hf_checkpoint.py
download.pyhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/download.py
download.pyhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/download.py
index.htmlhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/index.html
index.htmlhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/index.html
notes.txthttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/notes.txt
notes.txthttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/notes.txt
requirements.txthttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/requirements.txt
requirements.txthttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/requirements.txt
test.htmlhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/test.html
test.htmlhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/test.html
READMEhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Apache-2.0 licensehttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/blob/main/static/images/icons/MagicDec.png
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#-magicdec-breaking-throughput-latency-trade-off-for-long-context-generation--with-speculative-decoding
Jian Chen*https://github.com/jianc99
Vashisth Tiwari*https://github.com/Vashistht
Ranajoy Sadhukhan*https://github.com/ranonrkm
Zhuoming Chenhttps://github.com/dreaming-panda
Beidi Chenhttps://github.com/keroro824
Paperhttps://arxiv.org/abs/2408.11049
Bloghttps://infini-ai-lab.github.io/MagicDec
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#update
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#installation
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#environment-set-up
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#prepare-checkpoints
Llama-2-7bhttps://huggingface.co/meta-llama/Llama-2-7b-hf
Llama-2-7b-32khttps://huggingface.co/togethercomputer/LLaMA-2-7B-32K
Llama-2-13bhttps://huggingface.co/meta-llama/Llama-2-13b-hf
Llama-2-70bhttps://huggingface.co/meta-llama/Llama-2-70b-hf
Llama-3-8bhttps://huggingface.co/meta-llama/Meta-Llama-3-8B
Llama-3-70bhttps://huggingface.co/meta-llama/Meta-Llama-3-70B
llama-68mhttps://huggingface.co/JackFram/llama-68m
TinyLlamahttps://huggingface.co/TinyLlama/TinyLlama_v1.1
Llama-3.1-8bhttps://huggingface.co/meta-llama/Meta-Llama-3.1-8B
Llama-3.1-70bhttps://huggingface.co/meta-llama/Llama-3.1-70B
Llama-3.2-1bhttps://huggingface.co/meta-llama/Llama-3.2-1B
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#evaluations
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#baseline
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#standalone-draft
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#snapkv-based-drafting
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#streamingllm-based-drafting
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#self-speculation
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#snapkv-based-drafting-1
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#streamingllm-based-drafting-1
https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#citation
Readme https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#readme-ov-file
Apache-2.0 license https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec#Apache-2.0-1-ov-file
Please reload this pagehttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Activityhttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/activity
Custom propertieshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/custom-properties
142 starshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/stargazers
3 watchinghttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/watchers
9 forkshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/forks
Report repository https://patch-diff.githubusercontent.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2FInfini-AI-Lab%2FMagicDec&report=Infini-AI-Lab+%28user%29
Releaseshttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/releases
Packages 0https://patch-diff.githubusercontent.com/orgs/Infini-AI-Lab/packages?repo_name=MagicDec
Please reload this pagehttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Contributors 3https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/graphs/contributors
Please reload this pagehttps://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec
Python 47.7% https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/search?l=python
JavaScript 33.7% https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/search?l=javascript
HTML 18.0% https://patch-diff.githubusercontent.com/Infini-AI-Lab/MagicDec/search?l=html
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.