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
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 }}
The-Monk
/
llama.cpp
Public
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Actions: The-Monk/llama.cpp
Actions
All workflows
Workflows
.github/workflows/build-cann.yml
.github/workflows/build-cann.yml
.github/workflows/build-sycl.yml
.github/workflows/build-sycl.yml
Check Pre-Tokenizer Hashes
Check Pre-Tokenizer Hashes
Copilot Setup Steps
Copilot Setup Steps
Python check requirements.txt
Python check requirements.txt
Python Type-Check
Python Type-Check
Update Operations Documentation
Update Operations Documentation
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
27 workflow runs
27 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.
cuda: batched-decode mmvq tuning for RDNA4 binary/ternary types
.github/workflows/build-cann.yml
#14:
Commit
5de1c0d
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
cuda: rows_per_block=6 for Q1_0 decode on RDNA4 (+7%, re-swept post-r…
.github/workflows/build-cann.yml
#13:
Commit
7062917
pushed by
The-Monk
Failure
roc8
roc8
Failure
View workflow file
mmvq: fix ids-path OOB writes from partial rows_per_block blocks
.github/workflows/build-cann.yml
#12:
Commit
63a9969
pushed by
The-Monk
Failure
roc8-oob-fix
roc8-oob-fix
Failure
View workflow file
mmvq: chunked stream phases for fused gate+up (DRAM row-thrash mitiga…
.github/workflows/build-cann.yml
#11:
Commit
1838a7d
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
mmvq: fix ids-path OOB writes from partial rows_per_block blocks
.github/workflows/build-cann.yml
#10:
Commit
63a9969
pushed by
The-Monk
Failure
roc8-oob-fix
roc8-oob-fix
Failure
View workflow file
cuda: rows_per_block=6 for Q1_0 decode on RDNA4 (+7%, re-swept post-r…
Update Operations Documentation
#2:
Commit
7062917
pushed by
The-Monk
1d 0h 0m 10s
hackathon-2026-07-submission
hackathon-2026-07-submission
1d 0h 0m 10s
View workflow file
cuda: rows_per_block=6 for Q1_0 decode on RDNA4 (+7%, re-swept post-r…
Python Type-Check
#3:
Commit
7062917
pushed by
The-Monk
1d 0h 0m 2s
hackathon-2026-07-submission
hackathon-2026-07-submission
1d 0h 0m 2s
View workflow file
cuda: rows_per_block=6 for Q1_0 decode on RDNA4 (+7%, re-swept post-r…
Copilot Setup Steps
#1:
Commit
7062917
pushed by
The-Monk
1m 58s
hackathon-2026-07-submission
hackathon-2026-07-submission
1m 58s
View workflow file
cuda: rows_per_block=6 for Q1_0 decode on RDNA4 (+7%, re-swept post-r…
Check Pre-Tokenizer Hashes
#3:
Commit
7062917
pushed by
The-Monk
1d 0h 0m 2s
hackathon-2026-07-submission
hackathon-2026-07-submission
1d 0h 0m 2s
View workflow file
cuda: rows_per_block=6 for Q1_0 decode on RDNA4 (+7%, re-swept post-r…
Python check requirements.txt
#3:
Commit
7062917
pushed by
The-Monk
1d 0h 0m 2s
hackathon-2026-07-submission
hackathon-2026-07-submission
1d 0h 0m 2s
View workflow file
cuda: rows_per_block=6 for Q1_0 decode on RDNA4 (+7%, re-swept post-r…
.github/workflows/build-cann.yml
#9:
Commit
7062917
pushed by
The-Monk
-1s
roc8
roc8
-1s
View workflow file
roc10: mmvq ids-path OOB guard fix; dedup default-on; MUL_MAT+ADD res…
.github/workflows/build-cann.yml
#8:
Commit
d6116a0
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
roc10: Q1_0 decode rows_per_block 6 -> 4 (re-swept on the 2c-1 dp4a k…
.github/workflows/build-cann.yml
#7:
Commit
5e36c8d
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
roc10: slim mmvq to upstream structure, keep tuned RDNA4 launch geometry
.github/workflows/build-cann.yml
#6:
Commit
2cb75b8
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
roc10: base modernization — the full roc8 delta ported onto upstream …
Update Operations Documentation
#1:
Commit
2c1061f
pushed by
The-Monk
1d 0h 0m 1s
roc10
roc10
1d 0h 0m 1s
View workflow file
roc10: base modernization — the full roc8 delta ported onto upstream …
Python Type-Check
#2:
Commit
2c1061f
pushed by
The-Monk
1d 0h 0m 1s
roc10
roc10
1d 0h 0m 1s
View workflow file
roc10: base modernization — the full roc8 delta ported onto upstream …
Check Pre-Tokenizer Hashes
#2:
Commit
2c1061f
pushed by
The-Monk
1d 0h 0m 2s
roc10
roc10
1d 0h 0m 2s
View workflow file
roc10: base modernization — the full roc8 delta ported onto upstream …
Python check requirements.txt
#2:
Commit
2c1061f
pushed by
The-Monk
1d 0h 0m 2s
roc10
roc10
1d 0h 0m 2s
View workflow file
roc10: base modernization — the full roc8 delta ported onto upstream …
.github/workflows/build-cann.yml
#5:
Commit
2c1061f
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
cuda: rows_per_block=6 for Q1_0 decode on RDNA4 (+7%, re-swept post-r…
.github/workflows/build-cann.yml
#4:
Commit
7062917
pushed by
The-Monk
Failure
roc8
roc8
Failure
View workflow file
cuda: rewrite vec_dot_q1_0_q8_1 via the 2c-1 identity (+28% Q1_0 decode)
.github/workflows/build-cann.yml
#3:
Commit
3f7a40a
pushed by
The-Monk
Failure
roc8
roc8
Failure
View workflow file
test-backend-ops: cover MXFP6 decode and fp8 MoE (MUL_MAT_ID)
.github/workflows/build-cann.yml
#2:
Commit
56860a8
pushed by
The-Monk
Failure
roc8
roc8
Failure
View workflow file
cuda: AMD Q1_0/Q2_0 — HIP-path Q2_0 vec_dot, opt-in quant dedup, opt-…
Python Type-Check
#1:
Commit
4452cdb
pushed by
The-Monk
1d 0h 0m 2s
rdna4-q1q2
rdna4-q1q2
1d 0h 0m 2s
View workflow file
cuda: AMD Q1_0/Q2_0 — HIP-path Q2_0 vec_dot, opt-in quant dedup, opt-…
Python check requirements.txt
#1:
Commit
4452cdb
pushed by
The-Monk
1d 0h 0m 7s
rdna4-q1q2
rdna4-q1q2
1d 0h 0m 7s
View workflow file
cuda: AMD Q1_0/Q2_0 — HIP-path Q2_0 vec_dot, opt-in quant dedup, opt-…
Check Pre-Tokenizer Hashes
#1:
Commit
4452cdb
pushed by
The-Monk
1d 0h 0m 2s
rdna4-q1q2
rdna4-q1q2
1d 0h 0m 2s
View workflow file
Previous
1
2
Next
You can’t perform that action at this time.