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
.
taco-project
/
FlexKV
Public
Notifications
You must be signed in to change notification settings
Fork
63
Star
318
Code
Issues
10
Pull requests
20
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
Actions: taco-project/FlexKV
Actions
All workflows
Workflows
Copilot
Copilot
Copilot code review
Copilot code review
flexkv ci
flexkv ci
SWA Unit Smoke Pytest
SWA Unit Smoke Pytest
vLLM Compatibility Test
vLLM Compatibility Test
Show more workflows...
Management
Caches
All workflows
All workflows
Actions
Loading...
Loading
Sorry, something went wrong.
Uh oh!
There was an error while loading.
Please reload this page
.
will be ignored since log searching is not yet available
Showing runs from all workflows
will be ignored since log searching is not yet available
768 workflow runs
768 workflow runs
Workflow
Filter by Workflow
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching workflows.
Event
Filter by Event
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching events.
Status
Filter by Status
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching statuses.
Branch
Filter by Branch
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching branches.
Actor
Filter by Actor
Sorry, something went wrong.
Filter
Loading
Sorry, something went wrong.
No matching users.
refactor: split is_mla into orthogonal kv_dim + num_kv_heads
vLLM Compatibility Test
#231:
Pull request
#257
opened by
zhjc1124
4m 1s
zhjc1124:mla-refactor
zhjc1124:mla-refactor
4m 1s
View #257
View workflow file
refactor: split is_mla into orthogonal kv_dim + num_kv_heads
flexkv ci
#606:
Pull request
#257
opened by
zhjc1124
19m 36s
zhjc1124:mla-refactor
zhjc1124:mla-refactor
19m 36s
View #257
View workflow file
vLLM Compatibility Test
vLLM Compatibility Test
#230:
Scheduled
2m 57s
main
main
2m 57s
View workflow file
fix: per-node CPU/SSD pool sizing, PP-stage layer offset, and flush_cache deadlock for same-node PP>1
flexkv ci
#605:
Pull request
#256
synchronize by
zhjc1124
17m 50s
zhjc1124:fix/same-node-pp-pool-offset
zhjc1124:fix/same-node-pp-pool-offset
17m 50s
View #256
View workflow file
fix: per-node CPU/SSD pool sizing, PP-stage layer offset, and flush_cache deadlock for same-node PP>1
flexkv ci
#604:
Pull request
#256
synchronize by
zhjc1124
20m 50s
zhjc1124:fix/same-node-pp-pool-offset
zhjc1124:fix/same-node-pp-pool-offset
20m 50s
View #256
View workflow file
fix: per-node CPU/SSD pool sizing, PP-stage layer offset, and flush_cache deadlock for same-node PP>1
flexkv ci
#603:
Pull request
#256
synchronize by
zhjc1124
18m 35s
zhjc1124:fix/same-node-pp-pool-offset
zhjc1124:fix/same-node-pp-pool-offset
18m 35s
View #256
View workflow file
vLLM Compatibility Test
vLLM Compatibility Test
#229:
Scheduled
3m 14s
main
main
3m 14s
View workflow file
fix: per-node CPU/SSD pool sizing, PP-stage layer offset, and flush_cache deadlock for same-node PP>1
flexkv ci
#602:
Pull request
#256
synchronize by
zhjc1124
19m 30s
zhjc1124:fix/same-node-pp-pool-offset
zhjc1124:fix/same-node-pp-pool-offset
19m 30s
View #256
View workflow file
fix: per-node CPU/SSD pool sizing, PP-stage layer offset, and flush_cache deadlock for same-node PP>1
flexkv ci
#601:
Pull request
#256
synchronize by
zhjc1124
20m 16s
zhjc1124:fix/same-node-pp-pool-offset
zhjc1124:fix/same-node-pp-pool-offset
20m 16s
View #256
View workflow file
fix: per-node CPU/SSD pool sizing, PP-stage layer offset, and flush_cache deadlock for same-node PP>1
flexkv ci
#600:
Pull request
#256
synchronize by
zhjc1124
17m 15s
zhjc1124:fix/same-node-pp-pool-offset
zhjc1124:fix/same-node-pp-pool-offset
17m 15s
View #256
View workflow file
fix: per-node CPU/SSD pool sizing, PP-stage layer offset, and flush_cache deadlock for same-node PP>1
flexkv ci
#599:
Pull request
#256
synchronize by
zhjc1124
20m 11s
zhjc1124:fix/same-node-pp-pool-offset
zhjc1124:fix/same-node-pp-pool-offset
20m 11s
View #256
View workflow file
fix: per-node CPU/SSD pool sizing, PP-stage layer offset, and flush_cache deadlock for same-node PP>1
flexkv ci
#598:
Pull request
#256
opened by
zhjc1124
18m 0s
zhjc1124:fix/same-node-pp-pool-offset
zhjc1124:fix/same-node-pp-pool-offset
18m 0s
View #256
View workflow file
feat: extract sglang connector to FlexKV + config improvements (#255)
flexkv ci
#597:
Commit
4e29961
pushed by
linhu-nv
18m 15s
main
main
18m 15s
View workflow file
feat: extract sglang connector to FlexKV + config improvements
flexkv ci
#596:
Pull request
#255
synchronize by
zhjc1124
17m 49s
zhjc1124:refactor/sglang-connector-extraction
zhjc1124:refactor/sglang-connector-extraction
17m 49s
View #255
View workflow file
feat: extract sglang connector to FlexKV + config improvements
flexkv ci
#595:
Pull request
#255
synchronize by
zhjc1124
18m 45s
zhjc1124:refactor/sglang-connector-extraction
zhjc1124:refactor/sglang-connector-extraction
18m 45s
View #255
View workflow file
ci: fix wheel build, run CPU tests, and document CI/SGLang (#251)
flexkv ci
#594:
Commit
86b3c75
pushed by
linhu-nv
17m 43s
main
main
17m 43s
View workflow file
feat(vllm): support packed 4D KV cache layouts (#252)
flexkv ci
#593:
Commit
a79ddd5
pushed by
linhu-nv
9m 8s
main
main
9m 8s
View workflow file
feat(vllm): support packed 4D KV cache layouts (#252)
vLLM Compatibility Test
#228:
Commit
a79ddd5
pushed by
linhu-nv
2m 42s
main
main
2m 42s
View workflow file
vLLM Compatibility Test
vLLM Compatibility Test
#227:
Scheduled
3m 49s
main
main
3m 49s
View workflow file
feat: extract sglang connector to FlexKV + config improvements
flexkv ci
#592:
Pull request
#255
opened by
zhjc1124
10m 42s
zhjc1124:refactor/sglang-connector-extraction
zhjc1124:refactor/sglang-connector-extraction
10m 42s
View #255
View workflow file
vLLM Compatibility Test
vLLM Compatibility Test
#226:
Scheduled
2m 54s
main
main
2m 54s
View workflow file
vLLM Compatibility Test
vLLM Compatibility Test
#225:
Scheduled
3m 17s
main
main
3m 17s
View workflow file
feat(vllm): support packed 4D KV cache layouts
vLLM Compatibility Test
#224:
Pull request
#252
synchronize by
xuhao77
3m 21s
xuhao77:fix_vllm_4d_packed
xuhao77:fix_vllm_4d_packed
3m 21s
View #252
View workflow file
feat(vllm): support packed 4D KV cache layouts
flexkv ci
#591:
Pull request
#252
synchronize by
xuhao77
8m 50s
xuhao77:fix_vllm_4d_packed
xuhao77:fix_vllm_4d_packed
8m 50s
View #252
View workflow file
vLLM Compatibility Test
vLLM Compatibility Test
#223:
Scheduled
3m 32s
main
main
3m 32s
View workflow file
Previous
1
2
3
4
5
…
30
31
Next
You can’t perform that action at this time.