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 }}
QuixiAI
SlimServe
Repository navigation
Code
Issues
3
(3)
Pull requests
49
(49)
Actions
Projects
Security and quality
Insights
More
items
All pull requests
Labels
9
(9)
Milestones
0
(0)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
49
(49)
Closed
25
(25)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
LTX-2.5 audio+video generation on Apple Silicon: engine, seven Metal profiles (exact, HQ and fast tiers), serving
#86
·
auroter
opened
Oct 3, 2026
Contributor
·
·
1
#32 turns thinking off for all agentic traffic. This fixes it.
#85
·
auroter
opened
Sep 21, 2026
Contributor
·
·
1
Use BF16 target KV with XPU FlashAttention for Qwen3.8-27B
#84
·
ropoctl
opened
Sep 20, 2026
Contributor
·
5/5
·
·
1
Disable UR/XPTI tracing before XPU kernel initialization
#81
·
ropoctl
opened
Sep 20, 2026
Contributor
·
2/2
·
·
1
Keep trailing empty Responses items with their assistant tool turn
#80
·
ropoctl
opened
Sep 20, 2026
Contributor
·
2/2
·
·
1
Respect grammar masks when enforcing thinking budgets
#79
·
ropoctl
opened
Sep 20, 2026
Contributor
·
·
1
Document the B70 forward-port PRs and qualification limits
#72
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Add a multi-turn Responses tool protocol benchmark
#71
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Register a gated Qwen3.8-27B BF16 recipe for B70
#68
·
ropoctl
opened
Sep 19, 2026
Contributor
·
4/5
·
·
1
Register a gated Qwen3.8-27B Q8_K_P recipe for B70
#67
·
ropoctl
opened
Sep 19, 2026
Contributor
·
3/5
·
·
1
Register a gated Qwen3.8 FP8 recipe for four B70 GPUs
#66
·
ropoctl
opened
Sep 19, 2026
Contributor
·
2/5
·
·
1
Detect Intel Arc Pro B70 without initializing a GPU context
#65
·
ropoctl
opened
Sep 19, 2026
Contributor
·
1/5
·
·
1
Limit HSA host-staging probes to ROCm workers
#64
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Quiesce XPU workers before coordinated process teardown
#63
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Reuse split Q8 weights in XPU decode kernels
#62
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Add a Qwen tool-policy chat template with native thinking tokens
#61
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Authenticate registered Hugging Face downloads without losing resume headers
#60
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Allow XPU deployments to tune Triton softmax segment count
#59
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Mask unwritten tensor-descriptor tails before attention accumulation
#58
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Bound semantic checkpoint copies before rendering history
#57
·
ropoctl
opened
Sep 19, 2026
Contributor
·
2/2
·
·
1
Load embedded Qwen GGUF MTP heads without mutating the target
#56
·
ropoctl
opened
Sep 19, 2026
Contributor
·
2/2
·
·
1
Restore grouped GDN head layout when loading Qwen GGUF
#55
·
ropoctl
opened
Sep 19, 2026
Contributor
·
1/2
·
·
1
Honor thinking budgets in Responses sampling parameters
#54
·
ropoctl
opened
Sep 19, 2026
Contributor
·
·
1
Preserve streamed item identity in terminal Responses output
#53
·
ropoctl
opened
Sep 19, 2026
Contributor
·
4/4
·
·
1
Prevent required tool requests from stopping during reasoning
#52
·
ropoctl
opened
Sep 19, 2026
Contributor
·
3/4
·
·
1
Previous
1
2
Next
You can’t perform that action at this time.