Skip to content

Navigation Menu

Appearance settings

GitHub Copilot
Write better code with AI

GitHub Spark New
Build and deploy intelligent apps

GitHub Models New
Manage and compare prompts

GitHub Advanced Security
Find and fix vulnerabilities

Actions
Automate any workflow
Codespaces
Instant dev environments

Issues
Plan and track work

Code Review
Manage code changes

Discussions
Collaborate outside of code

Code Search
Find more, search less
Explore

Why GitHub

Documentation

GitHub Skills

Blog
Integrations

GitHub Marketplace

MCP Registry
View all features
By company size

Enterprises

Small and medium teams

Startups

Nonprofits
By use case

App Modernization

DevSecOps

DevOps

CI/CD

View all use cases
By industry

Healthcare

Financial services

Manufacturing

Government

View all industries
View all solutions
Topics

AI

DevOps

Security

Software Development

View all
Explore

Learning Pathways

Events & Webinars

Ebooks & Whitepapers

Customer Stories

Partners

Executive Insights
GitHub Sponsors
Fund open source developers
The ReadME Project
GitHub community articles
Repositories

Topics

Trending

Collections
Enterprise platform
AI-powered developer platform
Available add-ons

GitHub Advanced Security
Enterprise-grade security features

Copilot for business
Enterprise-grade AI features

Premium Support
Enterprise-grade 24/7 support
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

ggml-org / llama.cpp Public

Notifications You must be signed in to change notification settings
Fork 13.4k
Star 88k

Code
Issues 287
Pull requests 547
Discussions
Actions
Projects 10
Wiki
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security
Insights

llama : refactor sampling v2#9294

Merged

ggerganov merged 47 commits intomasterggml-org/llama.cpp:masterfrom

gg/llama-refactor-sampling-v2ggml-org/llama.cpp:gg/llama-refactor-sampling-v2Copy head branch name to clipboard

Sep 7, 2024

Conversation Commits47 (47)Checks Files changed

Merged

llama : refactor sampling v2#9294
ggerganov merged 47 commits intomasterfrom
gg/llama-refactor-sampling-v2

Commits

Commits on Sep 7, 2024

llama : add llama_sampling API + move grammar in libllama
ggerganov
committed
llama : sketching new sampling API
ggerganov
committed
cont : add llama_constraint_i [no ci]
ggerganov
committed
cont : initial implementation sketch [no ci]
ggerganov
committed
cont : fixes, naming [no ci]
ggerganov
committed
cont : add rest of the existing samplers [no ci]
ggerganov
committed
cont : fix [no ci]
ggerganov
committed
cont : add penalties and logit-bias constraints [no ci]
ggerganov
committed
cont : add comments [no ci]
ggerganov
committed
cont : leaner constraint initialization [no ci]
ggerganov
committed
cont : common/sampling use the new API [no ci]
ggerganov
committed
cont : add n_prev to llama_sampler_params
ggerganov
committed
cont : use new API in examples
ggerganov
committed
examples : fix build
ggerganov
committed
common : fix gpt_sampler_cp
ggerganov
committed
grammar : fix reset call
ggerganov
committed
constraint : clean-up and simplify
ggerganov
committed
constraint : add name API
ggerganov
committed
sampling : convert mirostat samplers to constraints
ggerganov
committed
sampler : API to iterate constraints
ggerganov
committed
sampling : simplify new llama_sampler calls
ggerganov
committed
sampling : simplify sample API
ggerganov
committed
sampling : fix grammar apply
ggerganov
committed
example : fix build + fix speculative
ggerganov
committed
sampling : remove top-k min_keep, fix mirostat init and state
ggerganov
committed
sampling : change _cp/copy to clone
ggerganov
committed
sampling : add name API + option to disable timings
ggerganov
committed
llama : restore comments in llama.h
ggerganov
committed
llama : remove llama_constraint
ggerganov
committed
sampling : fix cloning of samplers with null ctx
ggerganov
committed
ios : try to fix build
ggerganov
committed
sampling : improve mirostat implementation
ggerganov
committed
swift : fix example
ggerganov
committed
grammar : restore llama_grammar_accept signature
ggerganov
committed
sampling : allow passing m to mirostat sampler
ggerganov
committed
sampling : remove redundant indirection calls
ggerganov
committed
sampling : remove _context suffix [no ci]
ggerganov
committed
llama : add new llama_perf API
ggerganov
committed
common : simplify gpt_sampler
ggerganov
committed
batched.swift : fix build [no ci]
ggerganov
committed
examples : add missing samplers
ggerganov
committed
style : rearrange code + add comments and TODOs
ggerganov
committed
batched.swift : fix build
ggerganov
committed
sampling : avoid llama_model in few samplers
ggerganov
committed
sampling : fix state cloning
ggerganov
committed
sampling : fix repeat penalty out-of-bounds access
ggerganov
committed
llama : update doc [no ci]
ggerganov
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Community
Docs
Contact

You can’t perform that action at this time.