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 }}
bsreecharanreddy
dispatch
Repository navigation
Code
Issues
Pull requests
1
(1)
Actions
Projects
Security and quality
Insights
More
items
Phase 4: disaggregated prefill/decode
- #4
#4
Merged
bsreecharanreddy
merged 12 commits into
main
bsreecharanreddy/dispatch:main
from
phase-4-disaggregated-prefill-decode
bsreecharanreddy/dispatch:phase-4-disaggregated-prefill-decode
Copy head branch name to clipboard
Sep 17, 2026
Conversation
Commits
12
(12)
Checks
Files changed
Merged
Phase 4: disaggregated prefill/decode
#4
bsreecharanreddy
merged 12 commits into
main
bsreecharanreddy/dispatch:main
from
phase-4-disaggregated-prefill-decode
bsreecharanreddy/dispatch:phase-4-disaggregated-prefill-decode
Copy head branch name to clipboard
Commits
Commits on Sep 17, 2026
docs: Phase 4 design -- disaggregated prefill/decode
bsreecharanreddy
committed
a9ab18c
View commit details
Copy full SHA for a9ab18c
Browse repository at this point
docs: Phase 4 implementation plan -- disaggregated prefill/decode
bsreecharanreddy
committed
971ad91
View commit details
Copy full SHA for 971ad91
Browse repository at this point
feat: add KV-cache slice/pad-batch helpers for continuous batching
Show description for 6305fc3
bsreecharanreddy
committed
6305fc3
View commit details
Copy full SHA for 6305fc3
Browse repository at this point
feat: add cross-rank KV-cache handoff, proven over gloo
Show description for 911bb64
bsreecharanreddy
committed
911bb64
View commit details
Copy full SHA for 911bb64
Browse repository at this point
feat: add continuous-batching prefill and decode workers
Show description for 0c9ea77
bsreecharanreddy
committed
0c9ea77
View commit details
Copy full SHA for 0c9ea77
Browse repository at this point
feat: add co-located prefill/decode baseline worker
Show description for f78f9c3
bsreecharanreddy
committed
f78f9c3
View commit details
Copy full SHA for f78f9c3
Browse repository at this point
fix: make recv_kv_cache device-aware for NCCL
Show description for e864aa6
bsreecharanreddy
committed
e864aa6
View commit details
Copy full SHA for e864aa6
Browse repository at this point
fix: allocate pad_and_batch_caches' zero-padding on the cache's own device
Show description for 91a9f4e
bsreecharanreddy
committed
91a9f4e
View commit details
Copy full SHA for 91a9f4e
Browse repository at this point
fix: handle a rank receiving zero tokens for any local expert in local_expert_contribution
Show description for f68a8e8
bsreecharanreddy
committed
f68a8e8
View commit details
Copy full SHA for f68a8e8
Browse repository at this point
docs: record Phase 4 GPU runbook, cost, and correctness gate + concurrency results
Show description for a0106c7
bsreecharanreddy
committed
a0106c7
View commit details
Copy full SHA for a0106c7
Browse repository at this point
docs: record Phase 4 disaggregated prefill/decode outcome
Show description for abe8534
bsreecharanreddy
committed
abe8534
View commit details
Copy full SHA for abe8534
Browse repository at this point
docs: update README for Phase 4 completion
Show description for 83cc28c
bsreecharanreddy
committed
83cc28c
View commit details
Copy full SHA for 83cc28c
Browse repository at this point
You can’t perform that action at this time.