From 0ca54a5e76c0fa73522198cbeb742ad1e0e8d948 Mon Sep 17 00:00:00 2001 From: Artem Chumachenko Date: Thu, 11 Apr 2024 11:41:16 +0200 Subject: [PATCH] Rechain reloc --- .github/workflows/run-tests.yaml | 4 ++-- src/petals/server/throughput.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/workflows/run-tests.yaml b/.github/workflows/run-tests.yaml index 32baf11..d6316d4 100644 --- a/.github/workflows/run-tests.yaml +++ b/.github/workflows/run-tests.yaml @@ -14,8 +14,8 @@ jobs: - { model: 'bigscience/bloom-560m', os: 'ubuntu', python-version: '3.11' } - { model: 'Maykeye/TinyLLama-v0', os: 'ubuntu', python-version: '3.8' } - { model: 'Maykeye/TinyLLama-v0', os: 'ubuntu', python-version: '3.11' } - - { model: 'Maykeye/TinyLLama-v0', os: 'macos-14', python-version: '3.10' } - - { model: 'Maykeye/TinyLLama-v0', os: 'macos-14', python-version: '3.11' } + - { model: 'Maykeye/TinyLLama-v0', os: 'macos', python-version: '3.10' } + - { model: 'Maykeye/TinyLLama-v0', os: 'macos', python-version: '3.11' } - { model: 'artek0chumak/TestMixtral', os: 'ubuntu', python-version: '3.8' } - { model: 'artek0chumak/TestMixtral', os: 'ubuntu', python-version: '3.11' } fail-fast: false diff --git a/src/petals/server/throughput.py b/src/petals/server/throughput.py index 2302d3c..c30d287 100644 --- a/src/petals/server/throughput.py +++ b/src/petals/server/throughput.py @@ -206,7 +206,7 @@ def measure_compute_rps( block = block.to(dtype) block = convert_block(block, 0, config, tensor_parallel_devices, device, quant_type=quant_type, freeze=True) - cache = (DUMMY_KEY_PAST.to(dtype).to(device), DUMMY_KEY_PAST.to(dtype).to(device)) + cache = (DUMMY_KEY_PAST.to(dtype=dtype, device=device), DUMMY_KEY_PAST.to(dtype=dtype, device=device)) elapsed = 0 dummy_input = torch.randn(1, n_tokens, config.hidden_size, device=device, dtype=dtype)