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 }}
PrismML-Eng
/
llama.cpp
Public
forked from
ggml-org/llama.cpp
Notifications
You must be signed in to change notification settings
Fork
152
Star
786
Code
Issues
40
Pull requests
40
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
Actions: PrismML-Eng/llama.cpp
Actions
All workflows
Workflows
Release (Prism)
Release (Prism)
Build relocatable cmake package
Build relocatable cmake package
Check Pre-Tokenizer Hashes
Check Pre-Tokenizer Hashes
Check vendor
Check vendor
Code Style Checker
Code Style Checker
CodeQL
CodeQL
Convert PR to draft
Convert PR to draft
Copilot
Copilot
Copilot cloud agent
Copilot cloud agent
Copilot code review
Copilot code review
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
2,500+ workflow runs
2,500+ 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.
vulkan: add dedicated PQ2_0 mat-vec and BC-250 batch tuning
Server
#386:
Pull request
#281
opened by
renovys
Action required
renovys:bc250-pq2-matvec
renovys:bc250-pq2-matvec
Action required
View #281
View workflow file
vulkan: add dedicated PQ2_0 mat-vec and BC-250 batch tuning
Pull Request Labeler
#411:
Pull request
#281
opened by
renovys
39s
39s
View #281
View workflow file
metal : static-K32 tensor mul_mm for full-tile Q1_0 products (GGML_METAL_Q1_MM_K32=1)
Server
#385:
Pull request
#280
synchronize by
jasontitus
Action required
jasontitus:downstream/metal-q1-mm-k32
jasontitus:downstream/metal-q1-mm-k32
Action required
View #280
View workflow file
metal : static-K32 tensor mul_mm for full-tile Q1_0 products (GGML_METAL_Q1_MM_K32=1)
Pull Request Labeler
#410:
Pull request
#280
synchronize by
jasontitus
15s
15s
View #280
View workflow file
metal : opt-in PQ2_0 mat-vec for two columns (GGML_METAL_PQ2_MULTICOL=1)
Server
#384:
Pull request
#279
synchronize by
jasontitus
Action required
jasontitus:downstream/metal-pq2-multicol
jasontitus:downstream/metal-pq2-multicol
Action required
View #279
View workflow file
metal : opt-in PQ2_0 mat-vec for two columns (GGML_METAL_PQ2_MULTICOL=1)
Pull Request Labeler
#409:
Pull request
#279
synchronize by
jasontitus
32s
32s
View #279
View workflow file
metal : static-K32 tensor mul_mm for full-tile Q1_0 products (GGML_METAL_Q1_MM_K32=1)
Server
#383:
Pull request
#280
opened by
jasontitus
Action required
jasontitus:downstream/metal-q1-mm-k32
jasontitus:downstream/metal-q1-mm-k32
Action required
View #280
View workflow file
metal : static-K32 tensor mul_mm for full-tile Q1_0 products (GGML_METAL_Q1_MM_K32=1)
Pull Request Labeler
#408:
Pull request
#280
opened by
jasontitus
16s
16s
View #280
View workflow file
metal : opt-in PQ2_0 mat-vec for two columns (GGML_METAL_PQ2_MULTICOL=1)
Server
#382:
Pull request
#279
opened by
jasontitus
Action required
jasontitus:downstream/metal-pq2-multicol
jasontitus:downstream/metal-pq2-multicol
Action required
View #279
View workflow file
metal : opt-in PQ2_0 mat-vec for two columns (GGML_METAL_PQ2_MULTICOL=1)
Pull Request Labeler
#407:
Pull request
#279
opened by
jasontitus
22s
22s
View #279
View workflow file
sycl: dequantize PTQ1_0 and PQ2_0 prompt batches to FP16 (2-3x prompt processing)
Pull Request Labeler
#406:
Pull request
#278
opened by
dwymark
18s
18s
View #278
View workflow file
sycl: dequantize PTQ1_0 and PQ2_0 prompt batches to FP16 (2-3x prompt processing)
Server
#381:
Pull request
#278
opened by
dwymark
Action required
dwymark:sycl-fp16-prompt-gemm
dwymark:sycl-fp16-prompt-gemm
Action required
View #278
View workflow file
metal : PTQ1_0 multi-column mat-vec for 5-8 columns
Server
#380:
Pull request
#277
opened by
jasontitus
Action required
jasontitus:downstream/metal-ptq1-multicol-8
jasontitus:downstream/metal-ptq1-multicol-8
Action required
View #277
View workflow file
metal : PTQ1_0 multi-column mat-vec for 5-8 columns
Pull Request Labeler
#405:
Pull request
#277
opened by
jasontitus
19s
19s
View #277
View workflow file
qwen35 : in-place recurrent state rows for plain decode (GGML_GDN_ROWS_PLAIN=1)
Server
#379:
Pull request
#276
opened by
jasontitus
Action required
jasontitus:downstream/qwen35-gdn-rows-plain
jasontitus:downstream/qwen35-gdn-rows-plain
Action required
View #276
View workflow file
qwen35 : in-place recurrent state rows for plain decode (GGML_GDN_ROWS_PLAIN=1)
Pull Request Labeler
#404:
Pull request
#276
opened by
jasontitus
18s
18s
View #276
View workflow file
metal : split graphs into 4 command buffers on iOS
Server
#378:
Pull request
#275
opened by
jasontitus
Action required
jasontitus:downstream/metal-ios-command-buffers
jasontitus:downstream/metal-ios-command-buffers
Action required
View #275
View workflow file
metal : split graphs into 4 command buffers on iOS
Pull Request Labeler
#403:
Pull request
#275
opened by
jasontitus
16s
16s
View #275
View workflow file
vulkan: extend PTQ1_0 fast integer-dot path to INTEL_XE1 iGPUs (Arrow Lake-H)
Server
#377:
Pull request
#274
opened by
rriley-quorum
Action required
rriley-quorum:vulkan-arc-140t-ptq1-fix
rriley-quorum:vulkan-arc-140t-ptq1-fix
Action required
View #274
View workflow file
vulkan: extend PTQ1_0 fast integer-dot path to INTEL_XE1 iGPUs (Arrow Lake-H)
Pull Request Labeler
#402:
Pull request
#274
opened by
rriley-quorum
19s
19s
View #274
View workflow file
vulkan: dedicated mul_mat_vec shader for PTQ1_0 (~3x on the dequant path)
Server
#376:
Pull request
#252
synchronize by
Preygle
Action required
Preygle:vulkan-ptq1_0-mul-mat-vec
Preygle:vulkan-ptq1_0-mul-mat-vec
Action required
View #252
View workflow file
vulkan: dedicated mul_mat_vec shader for PTQ1_0 (~3x on the dequant path)
Pull Request Labeler
#401:
Pull request
#252
synchronize by
Preygle
16s
16s
View #252
View workflow file
Release (Prism)
Release (Prism)
#61:
Manually run by
khosravipasha
38m 29s
prism
prism
38m 29s
View workflow file
Push on prism
CodeQL
#249:
by
bri-prism
26m 3s
prism
prism
26m 3s
Push on prism
CodeQL
#248:
by
khosravipasha
16m 22s
prism
prism
16m 22s
Previous
1
2
3
4
5
…
99
100
101
Next
You can’t perform that action at this time.