Skip to content

Navigation Menu

Appearance settings

View all features
- 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
- 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
- COMMUNITY
  GitHub SponsorsFund open source developers
- PROGRAMS
  Security Lab
  Maintainer Community
  Accelerator
  Archive Program
- REPOSITORIES
  Topics
  Trending
  Collections
- ENTERPRISE SOLUTIONS
  Enterprise platformAI-powered developer platform
- AVAILABLE ADD-ONS
  GitHub Advanced SecurityEnterprise-grade security features
  Copilot for BusinessEnterprise-grade AI features
  Premium SupportEnterprise-grade 24/7 support
Pricing

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback

We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

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

janhq / llama.cpp Public

forked from ggml-org/llama.cpp

Notifications You must be signed in to change notification settings
Fork 3
Star 16

Code
Pull requests
Actions
Projects
Security
Insights

Additional navigation options

Code
Pull requests
Actions
Projects
Security
Insights

Sync master with upstream release b6027#182

Merged

jan-service-account merged 25 commits intodevjanhq/llama.cpp:devfrom

update-dev-from-master-2025-07-30-00-13janhq/llama.cpp:update-dev-from-master-2025-07-30-00-13Copy head branch name to clipboard

Jul 30, 2025

Conversation Commits25 (25)Checks Files changed

Merged

Sync master with upstream release b6027#182
jan-service-account merged 25 commits intodevfrom
update-dev-from-master-2025-07-30-00-13

Commits

Commits on Jul 27, 2025

llama : clarify comment about pp and tg graphs [no ci] (#14895)
danbev
authored
SYCL: add ops doc (#14901)
qnixsynapse
authored
vulkan: add ops docs (#14900)
0cc4m
authored
quantize : update README.md (#14905)

EAddario
and
CISC
authored

Commits on Jul 28, 2025

cmake : Indent ggml-config.cmake (ggml/1310)

dg0yt
authored and
ggerganov
committed
sync : ggml
ggerganov
committed
ops : update Metal (#14912)
ggerganov
authored
ops : update BLAS (#14914)
ggerganov
authored
sycl: refactor quantization to q8_1 (#14815)
Alcpz
authored
model : add support for SmallThinker series (#14898)

authored
CUDA: fix pointer incrementation in FA (#14916)
JohannesGaessler
authored
mtmd : add support for Voxtral (#14862)

ngxson
and
CISC
authored
SYCL: Add set_rows support for quantized types (#14883)
qnixsynapse
authored
ggml-cpu : deduplicate scalar implementations (#14897)
xctan
authored
llama-bench : use local GPUs along with RPC servers (#14917)
rgerganov
authored
test-backend-ops : extend test case filtering (#14865)
tlemo
authored
opencl : add ops docs (#14910)
lhez
authored

Commits on Jul 29, 2025

CUDA: add roll (#14919)
am17an
authored
server-bench: make seed choice configurable (#14929)

JohannesGaessler
and
CISC
authored
cuda : add softcap fusion (#14907)
CISC
authored
CANN: Add ggml_set_rows (#14943)
hipudding
authored
common : avoid logging partial messages (which can contain broken UTF-8 sequences) (#14937)
kallewoof
authored
HIP: Ignore unsupported unroll transformation in fattn-vec (#14931)
IMbackK
authored
HIP: add GGML_HIP_MMQ_MFMA option to allow disableing the MFMA path. (#14930)
IMbackK
authored
HIP: remove the use of __HIP_PLATFORM_AMD__, explicitly support only AMD targets (#14945)
IMbackK
authored

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Community
Docs
Contact

You can’t perform that action at this time.