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-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
.github/workflows/build-cann.yml
.github/workflows/build-cann.yml
Disabled
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
46 workflow runs
46 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.
rock8: MTP graft tool + ternary speculative decoding recipe (Q2_0 +21%)
Python Type-Check
#7:
Commit
d417f71
pushed by
The-Monk
1d 0h 0m 2s
rock8-release
rock8-release
1d 0h 0m 2s
View workflow file
rock8: MTP graft tool + ternary speculative decoding recipe (Q2_0 +21%)
.github/workflows/build-cann.yml
#23:
Commit
d417f71
pushed by
The-Monk
Failure
rock8-release
rock8-release
Failure
View workflow file
rock8: Strix Halo (gfx1151) tester notes
.github/workflows/build-cann.yml
#22:
Commit
7ca56e5
pushed by
The-Monk
Failure
rock8-release
rock8-release
Failure
View workflow file
rock8: all-AMD compatibility -- multi-arch fatbin builds clean gfx103…
Python Type-Check
#6:
Commit
7469ae6
pushed by
The-Monk
1d 0h 0m 1s
rock8-release
rock8-release
1d 0h 0m 1s
View workflow file
rock8: all-AMD compatibility -- multi-arch fatbin builds clean gfx103…
Copilot Setup Steps
#2:
Commit
7469ae6
pushed by
The-Monk
1m 51s
rock8-v1
rock8-v1
1m 51s
View workflow file
rock8: all-AMD compatibility -- multi-arch fatbin builds clean gfx103…
Python Type-Check
#5:
Commit
7469ae6
pushed by
The-Monk
1d 0h 0m 2s
rock8-v1
rock8-v1
1d 0h 0m 2s
View workflow file
rock8: all-AMD compatibility -- multi-arch fatbin builds clean gfx103…
Update Operations Documentation
#3:
Commit
7469ae6
pushed by
The-Monk
1d 0h 0m 2s
rock8-v1
rock8-v1
1d 0h 0m 2s
View workflow file
rock8: all-AMD compatibility -- multi-arch fatbin builds clean gfx103…
Check Pre-Tokenizer Hashes
#5:
Commit
7469ae6
pushed by
The-Monk
1d 0h 0m 2s
rock8-v1
rock8-v1
1d 0h 0m 2s
View workflow file
rock8: all-AMD compatibility -- multi-arch fatbin builds clean gfx103…
Python check requirements.txt
#5:
Commit
7469ae6
pushed by
The-Monk
1d 0h 0m 2s
rock8-v1
rock8-v1
1d 0h 0m 2s
View workflow file
rock8: all-AMD compatibility -- multi-arch fatbin builds clean gfx103…
.github/workflows/build-cann.yml
#21:
Commit
7469ae6
pushed by
The-Monk
Failure
rock8-release
rock8-release
Failure
View workflow file
rock8: all-AMD compatibility -- multi-arch fatbin builds clean gfx103…
.github/workflows/build-cann.yml
#20:
Commit
7469ae6
pushed by
The-Monk
Failure
rock8-release
rock8-release
Failure
View workflow file
ggml-cuda: SWAR unpack for q1_0/q2_0 on the HIP path (+30% prefill, +…
Python check requirements.txt
#4:
Commit
61dc603
pushed by
The-Monk
1d 0h 0m 2s
hip-q1q2-swar
hip-q1q2-swar
1d 0h 0m 2s
View workflow file
ggml-cuda: SWAR unpack for q1_0/q2_0 on the HIP path (+30% prefill, +…
Python Type-Check
#4:
Commit
61dc603
pushed by
The-Monk
1d 0h 0m 2s
hip-q1q2-swar
hip-q1q2-swar
1d 0h 0m 2s
View workflow file
ggml-cuda: SWAR unpack for q1_0/q2_0 on the HIP path (+30% prefill, +…
Check Pre-Tokenizer Hashes
#4:
Commit
61dc603
pushed by
The-Monk
1d 0h 0m 1s
hip-q1q2-swar
hip-q1q2-swar
1d 0h 0m 1s
View workflow file
ggml-cuda: SWAR unpack for q1_0/q2_0 on the HIP path (+30% prefill, +…
.github/workflows/build-cann.yml
#19:
Commit
61dc603
pushed by
The-Monk
Failure
hip-q1q2-swar
hip-q1q2-swar
Failure
View workflow file
mmq: SWAR tile unpack for q1_0/q2_0 -- kills the VCC select chains an…
.github/workflows/build-cann.yml
#18:
Commit
da53e9c
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
gated-delta-net: DPP wave reduction -- ds_bpermute off the token recu…
.github/workflows/build-cann.yml
#17:
Commit
ab69299
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
mmvq: F8E4M3 decode to T77 hardware-dot2 (lossless q8_1 activations)
.github/workflows/build-cann.yml
#16:
Commit
3ee043e
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
mmq: native MXFP6 tile -- unpack-to-e4m3 at tile load, reuse MXFP8 co…
.github/workflows/build-cann.yml
#15:
Commit
0925e6f
pushed by
The-Monk
Failure
roc10
roc10
Failure
View workflow file
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
Previous
1
2
Next
You can’t perform that action at this time.