Skip to content

Navigation Menu

Appearance settings

Explore
By company size
By use case
By industry
View all solutions
Topics
- AI
- DevOps
- Security
- Software Development
- View all
Explore
- GitHub Sponsors
  Fund open source developers
- The ReadME Project
  GitHub community articles
Repositories
- Enterprise platform
  AI-powered developer platform
Available add-ons
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

ggml-org / llama.cpp Public

Notifications You must be signed in to change notification settings
Fork 12.2k
Star 82.3k

Code
Issues 305
Pull requests 478
Discussions
Actions
Projects 10
Wiki
Security
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Wiki
Security
Insights

llama : add pipeline parallelism support#6017

Merged

slaren merged 23 commits intomasterggml-org/llama.cpp:masterfrom

sl/pipeline-parallelismggml-org/llama.cpp:sl/pipeline-parallelismCopy head branch name to clipboard

Mar 13, 2024

Conversation Commits23 (23)Checks Files changed

Merged

llama : add pipeline parallelism support#6017
slaren merged 23 commits intomasterfrom
sl/pipeline-parallelism

Commits

Commits on Mar 12, 2024

llama : add pipeline parallelism support for batch processing with multiple CUDA GPUs
slaren
committed
server : add -ub, --ubatch-size parameter
slaren
committed
fix server embedding test
slaren
committed
llama : fix Mamba inference for pipeline parallelism
compilade
committed
llama : limit max batch size to n_batch
slaren
committed
add LLAMA_SCHED_MAX_COPIES to configure the number of input copies for pipeline parallelism
slaren
committed
fix hip build
slaren
committed
Merge remote-tracking branch 'origin/master' into sl/pipeline-parallelism
slaren
committed
fix sycl build (disable cpy_tensor_async)
slaren
committed
fix hip build
slaren
committed

Commits on Mar 13, 2024

llama : limit n_batch and n_ubatch to n_ctx during context creation
slaren
committed
llama : fix norm backend
slaren
committed
batched-bench : sync after decode
ggerganov
committed
swiftui : sync after decode
ggerganov
committed
ggml : allow ggml_get_rows to use multiple threads if they are available
slaren
committed
check n_ubatch >= n_tokens with non-casual attention
slaren
committed
llama : do not limit n_batch to n_ctx with non-casual attn
slaren
committed
server : construct batch with size of llama_n_batch
ggerganov
committed
ggml_backend_cpu_graph_compute : fix return value when alloc fails
slaren
committed
llama : better n_batch and n_ubatch comment
slaren
committed
fix merge
slaren
committed
small fix
slaren
committed
reduce default n_batch to 2048
slaren
committed

Footer

© 2025 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Docs
Contact

You can’t perform that action at this time.