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
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
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 }}
JustVugg
colibri
Repository navigation
Code
Issues
44
(44)
Pull requests
82
(82)
Discussions
Actions
Projects
Security and quality
8
(8)
Insights
More
items
All pull requests
Labels
21
(21)
Milestones
0
(0)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
82
(82)
Closed
1,352
(1,352)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
fix(web): clean legacy storage even when preference writes fail
#2059
·
rudycelekli
opened
Oct 13, 2026
Contributor
·
·
fix(web): finish chat reads at the terminal SSE marker
#2058
·
rudycelekli
opened
Oct 13, 2026
Contributor
·
·
fix(web): assemble multiline chat SSE data before decoding
#2057
·
rudycelekli
opened
Oct 13, 2026
Contributor
·
·
fix(qwen36): cancel between CPU prefill chunks
#2056
·
Altroo
opened
Oct 13, 2026
·
3 tasks done
·
·
fix(tools): recover Qwen calls without losing ordinary text
#2055
·
Altroo
opened
Oct 13, 2026
·
3 tasks done
·
·
fix(qwen36): stop chat turns without cancellation errors
#2054
·
Altroo
opened
Oct 13, 2026
·
3 tasks done
·
·
fix(qwen36): advertise existing gateway tool support
#2053
·
Altroo
opened
Oct 13, 2026
·
3 tasks done
·
·
olmoe: batched GPU prefill for the CUDA library
#2052
·
qwzx4893-stack
opened
Oct 13, 2026
·
5 of 6 tasks
·
·
olmoe: GPU-resident batch-1 decode as an opt-in library (olmoe_cuda.h)
#2051
·
qwzx4893-stack
opened
Oct 13, 2026
·
5 of 6 tasks
·
·
[Draft] kolibri1: experimental CPU engine for Aleph Alpha Kolibri-1 (qualification incomplete)
#2049
·
bokiko
opened
Oct 13, 2026
Contributor
·
3 of 5 tasks
·
·
feat(qwenimage): image editing support across API, CLI, engine, and UI (#2044)
#2045
·
Suraj2105-1
opened
Oct 12, 2026
Contributor
·
11 tasks done
·
·
1
feat(olmoe): GPU-resident OLMoE decode and batched prefill (opt-in CUDA library)
#2043
·
Suraj2105-1
opened
Oct 12, 2026
Contributor
·
9 tasks done
·
·
idot: add SSSE3 (128-bit) integer-dot kernels for pre-AVX2 x86-64
#2042
·
ggeorgovassilis
opened
Oct 12, 2026
·
·
olmoe: keep attention and lm_head half-resident (bit-identical, -0.7 GB RSS, +26% cached decode)
#2041
·
qwzx4893-stack
opened
Oct 12, 2026
·
6 of 7 tasks
·
·
olmoe: FUSED3 must follow IDOT; it is lossy by design, not "bit-exact"
#2039
·
qwzx4893-stack
opened
Oct 12, 2026
·
6 of 7 tasks
·
·
fix(setup): preserve --ctx on resume and allow automatic reset
#2038
·
Stamina9
opened
Oct 12, 2026
Contributor
·
6 of 7 tasks
·
·
windows: a shard's readers overlap through a second descriptor
#2037
·
namespaceMarcello
opened
Oct 12, 2026
Contributor
·
5 of 6 tasks
·
·
qwen36: the expert load keeps its scratch block
#2035
·
namespaceMarcello
opened
Oct 11, 2026
Contributor
·
5 of 6 tasks
·
·
2
qwen36: a prompt's rows reach the expert kernel in runs as large as the cache holds
#2034
·
namespaceMarcello
opened
Oct 11, 2026
Contributor
·
5 of 6 tasks
·
·
fix(audio): reject truncated WAV chunks and incomplete frames
#2023
·
rudycelekli
opened
Oct 11, 2026
Contributor
·
3 tasks done
·
·
fix: validate decision-model weight payloads before RAM estimates
#2022
·
rudycelekli
opened
Oct 11, 2026
Contributor
·
·
fix: preserve Unicode separators inside benchmark JSONL prompts
#2021
·
rudycelekli
opened
Oct 11, 2026
Contributor
·
·
fix: verify mirror shards against current model bytes
#2020
·
rudycelekli
opened
Oct 11, 2026
Contributor
·
·
fix: reject benchmark downloads with no usable rows
#2019
·
rudycelekli
opened
Oct 11, 2026
Contributor
·
·
fix(setup): apply RAM plans for CPU and Vulkan installs
#2018
·
rudycelekli
opened
Oct 10, 2026
Contributor
·
·
Previous
1
2
3
4
Next
You can’t perform that action at this time.