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 }}
kmbandy
/
llama.cpp
Public
forked from
ggml-org/llama.cpp
Notifications
You must be signed in to change notification settings
Fork
0
Star
5
Code
Issues
0
Pull requests
1
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
Actions: kmbandy/llama.cpp
Actions
All workflows
Workflows
.github/workflows/build-cann.yml
.github/workflows/build-cann.yml
AI review (issues)
AI review (issues)
Build Actions Cache
Build Actions Cache
Build relocatable cmake package
Build relocatable cmake package
Check Pre-Tokenizer Hashes
Check Pre-Tokenizer Hashes
Check vendor
Check vendor
CI (3rd-party)
CI (3rd-party)
CI (android)
CI (android)
CI (apple)
CI (apple)
CI (army — paged + tiered KV)
CI (army — paged + tiered KV)
Show more workflows...
Management
Caches
CI (android)
CI (android)
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
Show workflow options
Create status badge
Create status badge
Loading
Uh oh!
There was an error while loading.
Please reload this page
.
build-android.yml
will be ignored since log searching is not yet available
145 workflow runs
145 workflow runs
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.
llama-model-loader: LLAMA_MMAP_SIDECAR_ONLY per-file mmap (spine RSS …
CI (android)
#145:
Commit
c4a4ddc
pushed by
kmbandy
In progress
master
master
In progress
View workflow file
wp dispatch: threaded ml8_4 encode and stream send overlap (205 -> 23…
CI (android)
#144:
Commit
6e84c83
pushed by
kmbandy
2m 52s
master
master
2m 52s
View workflow file
wp worker: working RAM-tier admission for prefill, layer-ahead depth N
CI (android)
#143:
Commit
1c671e3
pushed by
kmbandy
2m 45s
master
master
2m 45s
View workflow file
wp dispatch: partial unpack options and one-pass scan+copy for stream…
CI (android)
#142:
Commit
5494ee2
pushed by
kmbandy
2m 26s
master
master
2m 26s
View workflow file
wp dispatch: pack a layer's activations once, slice them per worker a…
CI (android)
#141:
Commit
cb1029d
pushed by
kmbandy
2m 5s
master
master
2m 5s
View workflow file
wp dispatch: plan and stream-encode time in WP_DS4_LAYER_TRACE
CI (android)
#140:
Commit
4e70e2e
pushed by
kmbandy
2m 43s
master
master
2m 43s
View workflow file
deepseek41: WP_DSV41_SPARSE_ATTN_DIFF debug knob
CI (android)
#139:
Commit
adf6d65
pushed by
kmbandy
2m 2s
master
master
2m 2s
View workflow file
ci : key cache to sanitizer matrix (#28708)
CI (android)
#138:
Pull request
#17
synchronize by
kmbandy
4m 18s
claude/hello-ky3ivj
claude/hello-ky3ivj
4m 18s
View #17
View workflow file
ci : key cache to sanitizer matrix (#28708)
CI (android)
#137:
Pull request
#17
opened by
kmbandy
4m 14s
claude/hello-ky3ivj
claude/hello-ky3ivj
4m 14s
View #17
View workflow file
deepseek41: prefill path, sparse attention, and wp-forge expert-id re…
CI (android)
#136:
Commit
26e5f58
pushed by
kmbandy
2m 12s
master
master
2m 12s
View workflow file
wp-expert-worker: accept --host-tier-bytes 0 (retain nothing; the pre…
CI (android)
#135:
Commit
b10caf2
pushed by
kmbandy
3m 6s
master
master
3m 6s
View workflow file
wp-expert-worker: pin every expert mul_mat by default (WP_EXPERT_MM_P…
CI (android)
#134:
Commit
81ca5b5
pushed by
kmbandy
3m 22s
master
master
3m 22s
View workflow file
wp-expert-worker: WP_EXPERT_MM_PIN=all pins every expert mul_mat at e…
CI (android)
#133:
Commit
525ceaa
pushed by
kmbandy
2m 3s
master
master
2m 3s
View workflow file
wp-expert-worker: re-review fixes -- serial read_worker points the re…
CI (android)
#132:
Commit
3235029
pushed by
kmbandy
1m 57s
master
master
1m 57s
View workflow file
hip: fix other-arch stubs so gfx1201-only GEMM units build for gfx1030
CI (android)
#131:
Commit
7fe94fe
pushed by
kmbandy
2m 27s
master
master
2m 27s
View workflow file
ml8-4 prod: libr4d attention on ml8-4 KV, fused qrot glue, concat/cpy…
CI (android)
#130:
Commit
55bc7c6
pushed by
kmbandy
1m 58s
master
master
1m 58s
View workflow file
Merge remote-tracking branch 'origin/master'
CI (android)
#129:
Commit
16f8ea1
pushed by
kmbandy
1m 54s
master
master
1m 54s
View workflow file
cuda/allreduce: fix CUDA build of the spin-budget/watchdog code
CI (android)
#128:
Commit
c3184a4
pushed by
kmbandy
2m 7s
master
master
2m 7s
View workflow file
ggml-backend-meta: keep now_ns unconditional so GGML_META_STEP_STATS …
CI (android)
#127:
Commit
cc1389a
pushed by
kmbandy
3m 2s
master
master
3m 2s
View workflow file
Merge branch 'wp/draft-mmvq'
CI (android)
#126:
Commit
d6e7955
pushed by
kmbandy
2m 12s
master
master
2m 12s
View workflow file
wp-forge: DeepSeek-V4.1-Flash plan of record
CI (android)
#125:
Commit
fa09400
pushed by
kmbandy
4m 48s
master
master
4m 48s
View workflow file
fix(pipeline): chunked dispatch - custom ops tolerate a multi-thread …
CI (android)
#124:
Commit
2cbdf75
pushed by
kmbandy
7m 31s
master
master
7m 31s
View workflow file
fix(pipeline): chunked dispatch - idempotent issue replay + begin_dis…
CI (android)
#123:
Commit
f79a00b
pushed by
kmbandy
8m 40s
master
master
8m 40s
View workflow file
fix(pipeline): chunked dispatch - hold dispatcher io mutex across the…
CI (android)
#122:
Commit
94b77e5
pushed by
kmbandy
8m 1s
master
master
8m 1s
View workflow file
feat(pipeline): WP_DISPATCH_CHUNKS=2 - intra-layer chunked expert dis…
CI (android)
#121:
Commit
48c10b7
pushed by
kmbandy
7m 45s
master
master
7m 45s
View workflow file
Previous
1
2
3
4
5
6
Next
You can’t perform that action at this time.