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 }}
mudler
/
vllm.cpp
Public
Notifications
You must be signed in to change notification settings
Fork
54
Star
443
Code
Issues
357
Pull requests
19
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
All pull requests
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
19
(19)
Closed
607
(607)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
More items
Comfortable display density
Compact display density
feat(TT-KEEPQUANT): the INT8DOT default flip — band-gated on the live arm, 4.69x on the default path
#3397
·
lu-zero
opened
Oct 4, 2026
Collaborator
·
·
fix(records): bring the aleph-alpha-inference oracle pin inside the s…
#3395
·
phantomic12
opened
Oct 4, 2026
Contributor
·
5 tasks
·
·
fix(ORACLE-PIN-SURFACES): restate the a7c23ac96d pin, and re-anchor every claim the substitution made false
#3391
·
phantomic12
opened
Oct 4, 2026
Contributor
·
·
fix(ci): match the FLASH_ATTN pin as a fixed string, not a BRE
#3390
·
phantomic12
opened
Oct 4, 2026
Contributor
·
·
docs(ENG-MM-INPUT-PIPELINE): explain media limits
#3389
·
localai-org-maint-bot
opened
Oct 4, 2026
Collaborator
·
8 of 9 tasks
·
·
docs: correct Qwen3.8-27B quantized support guidance
documentation
#3381
·
localai-org-maint-bot
opened
Oct 3, 2026
Collaborator
·
·
feat(vulkan): native kCausalConv1dFwd, the GDN prefill conv
#3368
·
allenk
opened
Oct 1, 2026
·
3 of 4 tasks
·
·
record(ENG-RECORD-CONFLICT-SURFACES): retire eleven dangling checker-line citations, five to symbol anchors and six to retirement prose
#3367
·
phantomic12
opened
Oct 1, 2026
Contributor
·
·
fix(tokenizer): resolve eos/bos ids from tokenizer_config.json (MODEL-QWEN35-EXL3)
#3363
·
ghazni101
opened
Sep 30, 2026
Contributor
·
·
1
perf(KV-FP8): serve fp8 KV prefill through the bf16 dense dequant
#3360
·
iiLaurens
opened
Sep 29, 2026
Contributor
·
3 of 4 tasks
·
·
2
feat(ENG-HOST-EMBEDDING): gather the token table on the host
#3356
·
iiLaurens
opened
Sep 29, 2026
Contributor
·
6 tasks done
·
·
2
record(ENG-RECORD-CONFLICT-SURFACES): retire the dangling check-agent-record.py line 1973 citation from row 898 and ISSUE-GH-2317
#3354
·
phantomic12
opened
Sep 29, 2026
Contributor
·
·
fix(ENG-RECORD-ANCHOR-RATCHET): restore the 35 definitions c12b376b2 deleted, unwired, and measure the rot they had been hiding
#3344
·
phantomic12
opened
Sep 28, 2026
Contributor
·
·
docs(SERVE-C-ABI): align ABI 30 audio documentation
#3343
·
localai-org-maint-bot
opened
Sep 28, 2026
Collaborator
·
9 of 10 tasks
·
·
fix(GATE-ISSUE-INDEX-TABLE-SHAPE): declare the three rows their own specs name, so the issue index can validate a record again
#3342
·
phantomic12
opened
Sep 28, 2026
Contributor
·
·
1
fix(ENG-PUBLIC-DOC-PROJECTIONS): add the benchmark index table the checker has required since the day it was written
#3339
·
phantomic12
opened
Sep 28, 2026
Contributor
·
·
1
fix(ORACLE-PIN-SURFACES): restate the a7c23ac96d pin, and re-anchor every claim the substitution made false
#3335
·
phantomic12
opened
Sep 27, 2026
Contributor
·
·
2
fix(BACKEND-VULKAN): correct three false records about the B60; VK-I's staging half is answered by ReBAR
#3334
·
phantomic12
opened
Sep 27, 2026
Contributor
·
·
2
fix(records): add a scoped .gitattributes line-ending policy so the byte-exact issue index can pass
#3333
·
phantomic12
opened
Sep 27, 2026
Contributor
·
·
You can’t perform that action at this time.