Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
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
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
Accelerator
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
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
Type
/
to search
Sign in
Sign up
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
{{ message }}
Uh oh!
There was an error while loading.
Please reload this page
.
Infini-AI-Lab
/
vortex_torch
Public
Notifications
You must be signed in to change notification settings
Fork
12
Star
68
Code
Issues
0
Pull requests
6
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
Vortex quantization and topk kernel adaption
- #1
#1
Open
zxr-creator
wants to merge 25 commits into
Infini-AI-Lab:v1
Infini-AI-Lab/vortex_torch:v1
from
zxr-creator:v1
zxr-creator/vortex_torch:v1
Copy head branch name to clipboard
Conversation
Commits
25
(25)
Checks
Files changed
Open
Vortex quantization and topk kernel adaption
#1
zxr-creator
wants to merge 25 commits into
Infini-AI-Lab:v1
Infini-AI-Lab/vortex_torch:v1
from
zxr-creator:v1
zxr-creator/vortex_torch:v1
Copy head branch name to clipboard
Commits
Commits on Feb 22, 2026
Add int8 quantization for vortex.
Show description for 6077fea
zxr-creator
committed
6077fea
View commit details
Copy full SHA for 6077fea
Browse repository at this point
Commits on Feb 23, 2026
1. Add support for pro 6000. 2. Correction for vortex
zxr-creator
committed
1f52772
View commit details
Copy full SHA for 1f52772
Browse repository at this point
1. Correction on int8 (maximize memory occupation) 2. Implement fp8 quantization.
zxr-creator
committed
584f233
View commit details
Copy full SHA for 584f233
Browse repository at this point
Commits on Mar 1, 2026
update on parameters for reduce_pp_kernel with quantization
zxr-creator
committed
f25fb13
View commit details
Copy full SHA for f25fb13
Browse repository at this point
Commits on Mar 2, 2026
adapt topk kernel from sglang to vortex
zxr-creator
committed
b9eb717
View commit details
Copy full SHA for b9eb717
Browse repository at this point
Commits on Mar 9, 2026
add parameter to switch between two topk kernels (naive or sglang)
zxr-creator
committed
ede8624
View commit details
Copy full SHA for ede8624
Browse repository at this point
add parameter to switch between two topk kernels (naive or sglang)
zxr-creator
committed
edbf789
View commit details
Copy full SHA for edbf789
Browse repository at this point
Commits on Mar 18, 2026
add aim24
zxr-creator
committed
87d7664
View commit details
Copy full SHA for 87d7664
Browse repository at this point
Commits on Mar 24, 2026
Implement sparse prefill with topk on a new ragged only warpper
zxr-creator
committed
66237d7
View commit details
Copy full SHA for 66237d7
Browse repository at this point
Merge pull request #1 from zxr-creator/24b09b6
Show description for 4bd84c9
zxr-creator
authored
4bd84c9
View commit details
Copy full SHA for 4bd84c9
Browse repository at this point
Commits on Mar 29, 2026
fix on the ragged warpper, using single ragged warpper on concated rags and pages; fix on the previous quantization implementaion, with lanuch_graph dtype set to the quant type
zxr-creator
committed
9a73a8c
View commit details
Copy full SHA for 9a73a8c
Browse repository at this point
Commits on Mar 30, 2026
Sparse attention kernel apdation with full attention kernels, include (naive sparse attention, flash sparse attention, flashmoba)
zxr-creator
committed
a8fd328
View commit details
Copy full SHA for a8fd328
Browse repository at this point
Refactor on the int8 quanitzation, mainly the dequant kernels of int8
zxr-creator
committed
f6ca879
View commit details
Copy full SHA for f6ca879
Browse repository at this point
Commits on Mar 31, 2026
Add TopK benchmarking suite and related scripts
Show description for 19c7fcc
zxr-creator
committed
19c7fcc
View commit details
Copy full SHA for 19c7fcc
Browse repository at this point
Commits on Apr 1, 2026
Enhance TopK mapping modes with new remap functions
Show description for 31ba23b
zxr-creator
committed
31ba23b
View commit details
Copy full SHA for 31ba23b
Browse repository at this point
Commits on Apr 2, 2026
enhance TopK mapping with adaptive tail-window mode; modify example scripts to reflect changes in histogram calibration and TopK mapping parameters.
zxr-creator
committed
15f1d03
View commit details
Copy full SHA for 15f1d03
Browse repository at this point
Commits on Apr 7, 2026
Enhance TopK mapping with new modes and original sglang kernel support
Show description for 080c253
zxr-creator
committed
080c253
View commit details
Copy full SHA for 080c253
Browse repository at this point
Update TopK mapping and profiling functionalities
Show description for e6b73e4
zxr-creator
committed
e6b73e4
View commit details
Copy full SHA for e6b73e4
Browse repository at this point
Commits on Apr 13, 2026
Refactor TopK mapping and benchmarking scripts for enhanced profiling and usability
Show description for 524834a
zxr-creator
committed
524834a
View commit details
Copy full SHA for 524834a
Browse repository at this point
Refactor TopK mapping and benchmarking scripts for enhanced profiling and usability
Show description for aecde11
zxr-creator
committed
aecde11
View commit details
Copy full SHA for aecde11
Browse repository at this point
Commits on Apr 14, 2026
- Introduced topk_output_sglang_ori function for the original SGLang kernel in vortex_torch_C.
Show description for 990b3eb
zxr-creator
committed
990b3eb
View commit details
Copy full SHA for 990b3eb
Browse repository at this point
Commits on Apr 15, 2026
Enhance TopK benchmarking and calibration scripts
Show description for fe0b8e2
zxr-creator
committed
fe0b8e2
View commit details
Copy full SHA for fe0b8e2
Browse repository at this point
Commits on Apr 19, 2026
Add parallel TopK kernel and profiling enhancements
Show description for 13cb8a0
zxr-creator
committed
13cb8a0
View commit details
Copy full SHA for 13cb8a0
Browse repository at this point
Commits on Apr 20, 2026
Add new TopK cluster and fast merge kernels, update profiling and benchmarking
Show description for 28ccd85
zxr-creator
committed
28ccd85
View commit details
Copy full SHA for 28ccd85
Browse repository at this point
Commits on Apr 26, 2026
Update TopK kernel implementations and benchmarking scripts
Show description for fb43744
zxr-creator
committed
fb43744
View commit details
Copy full SHA for fb43744
Browse repository at this point
You can’t perform that action at this time.
