From f30ea47a87ed4446ad55adb265755dc9102956a2 Mon Sep 17 00:00:00 2001 From: slaren Date: Wed, 13 Mar 2024 18:54:21 +0100 Subject: llama : add pipeline parallelism support (#6017) * 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 Co-authored-by: Georgi Gerganov --- examples/server/tests/features/steps/steps.py | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'examples/server/tests/features/steps/steps.py') diff --git a/examples/server/tests/features/steps/steps.py b/examples/server/tests/features/steps/steps.py index 98c2b617..cfa9f96e 100644 --- a/examples/server/tests/features/steps/steps.py +++ b/examples/server/tests/features/steps/steps.py @@ -33,6 +33,7 @@ def step_server_config(context, server_fqdn, server_port): context.model_alias = None context.n_batch = None + context.n_ubatch = None context.n_ctx = None context.n_ga = None context.n_ga_w = None @@ -278,6 +279,11 @@ def step_n_batch(context, n_batch): context.n_batch = n_batch +@step('{n_ubatch:d} as ubatch size') +def step_n_ubatch(context, n_ubatch): + context.n_ubatch = n_ubatch + + @step('{seed:d} as seed') def step_seed(context, seed): context.seed = seed @@ -1029,6 +1035,8 @@ def start_server_background(context): ] if context.n_batch: server_args.extend(['--batch-size', context.n_batch]) + if context.n_ubatch: + server_args.extend(['--ubatch-size', context.n_ubatch]) if context.n_gpu_layer: server_args.extend(['--n-gpu-layers', context.n_gpu_layer]) if context.server_continuous_batching: -- cgit v1.2.3