* llama : add pipeline parallelism support for batch processing with multiple CUDA GPUs ggml-ci * server : add -ub, --ubatch-size parameter * fix server embedding test * llama : fix Mamba inference for pipeline parallelism Tested to work correctly with both `main` and `parallel` examples. * llama : limit max batch size to n_batch * add LLAMA_SCHED_MAX_COPIES to configure the number of input copies for pipeline parallelism default increase to 4 (from 2) changing this value may improve performance for some systems, but increases memory usage * fix hip build * fix sycl build (disable cpy_tensor_async) * fix hip build * llama : limit n_batch and n_ubatch to n_ctx during context creation * llama : fix norm backend * batched-bench : sync after decode * swiftui : sync after decode * ggml : allow ggml_get_rows to use multiple threads if they are available * check n_ubatch >= n_tokens with non-casual attention * llama : do not limit n_batch to n_ctx with non-casual attn * server : construct batch with size of llama_n_batch * ggml_backend_cpu_graph_compute : fix return value when alloc fails * llama : better n_batch and n_ubatch comment * fix merge * small fix * reduce default n_batch to 2048 --------- Co-authored-by: Francis Couture-Harpin <git@compilade.net> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> |
||
---|---|---|
.. | ||
llama.cpp.swift | ||
llama.swiftui | ||
llama.swiftui.xcodeproj | ||
.gitignore | ||
README.md |
llama.cpp/examples/llama.swiftui
Local inference of llama.cpp on an iPhone. This is a sample app that can be used as a starting point for more advanced projects.
For usage instructions and performance stats, check the following discussion: https://github.com/ggerganov/llama.cpp/discussions/4508
Video demonstration:
https://github.com/bachittle/llama.cpp/assets/39804642/e290827a-4edb-4093-9642-2a5e399ec545