Alexander Borzunov de2475f31c Make client compatible with transformers' GenerationMixin (#464) %!s(int64=2) %!d(string=hai) anos
..
bootstrap.id 8c546d988a Test Llama, rebalancing, throughput eval, and all CLI scripts (#452) %!s(int64=2) %!d(string=hai) anos
conftest.py 668b736031 Fix logging: do not duplicate lines, enable colors in Colab (#156) %!s(int64=2) %!d(string=hai) anos
server2.id 8c546d988a Test Llama, rebalancing, throughput eval, and all CLI scripts (#452) %!s(int64=2) %!d(string=hai) anos
test_aux_functions.py 568f21dc3b Add customizable input tensors (#445) %!s(int64=2) %!d(string=hai) anos
test_block_exact_match.py 056f22515a Prioritize short inference, unmerge pools for long inference (#458) %!s(int64=2) %!d(string=hai) anos
test_chained_calls.py 8c546d988a Test Llama, rebalancing, throughput eval, and all CLI scripts (#452) %!s(int64=2) %!d(string=hai) anos
test_dtype.py cb3f018f9f Add LLaMA support (#323) %!s(int64=2) %!d(string=hai) anos
test_full_model.py de2475f31c Make client compatible with transformers' GenerationMixin (#464) %!s(int64=2) %!d(string=hai) anos
test_peft.py b9f0a5467f Support peft LoRA adapters (#335) %!s(int64=2) %!d(string=hai) anos
test_priority_pool.py 523a7cad33 Fix issues related to `petals` as a module (#159) %!s(int64=2) %!d(string=hai) anos
test_remote_sequential.py 329f7d31e8 Add `blocked_servers` argument (#462) %!s(int64=2) %!d(string=hai) anos
test_sequence_manager.py 8c546d988a Test Llama, rebalancing, throughput eval, and all CLI scripts (#452) %!s(int64=2) %!d(string=hai) anos
test_server_stats.py 8c546d988a Test Llama, rebalancing, throughput eval, and all CLI scripts (#452) %!s(int64=2) %!d(string=hai) anos
test_tensor_parallel.py 8c546d988a Test Llama, rebalancing, throughput eval, and all CLI scripts (#452) %!s(int64=2) %!d(string=hai) anos
test_utils.py b9f0a5467f Support peft LoRA adapters (#335) %!s(int64=2) %!d(string=hai) anos