You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Anton Sinitsin c0a4d2e3d5 Add option to rollback inference for a certain number of steps (#588) ... * fix * fix * fix * fix * fix * fix * style		3 months ago
..
bootstrap.id	Test Llama, rebalancing, throughput eval, and all CLI scripts (#452)	1 year ago
conftest.py	Fix logging: do not duplicate lines, enable colors in Colab (#156)	2 years ago
server2.id	Test Llama, rebalancing, throughput eval, and all CLI scripts (#452)	1 year ago
test_aux_functions.py	Add customizable input tensors (#445)	1 year ago
test_block_exact_match.py	Prioritize short inference, unmerge pools for long inference (#458)	1 year ago
test_cache.py	Support macOS (#477)	1 year ago
test_chained_calls.py	Fix Mixtral-related issues (#570)	6 months ago
test_dtype.py	Add LLaMA support (#323)	1 year ago
test_full_model.py	Fix Mixtral-related issues (#570)	6 months ago
test_optimized_layers.py	Fix Mixtral-related issues (#570)	6 months ago
test_peft.py	Support peft LoRA adapters (#335)	1 year ago
test_priority_pool.py	Support macOS (#477)	1 year ago
test_remote_sequential.py	Fix `.generate(input_ids=...)` (#485)	1 year ago
test_sequence_manager.py	Test Llama, rebalancing, throughput eval, and all CLI scripts (#452)	1 year ago
test_server_stats.py	Test Llama, rebalancing, throughput eval, and all CLI scripts (#452)	1 year ago
test_speculative_generation.py	Add option to rollback inference for a certain number of steps (#588)	3 months ago
test_tensor_parallel.py	Test Llama, rebalancing, throughput eval, and all CLI scripts (#452)	1 year ago
test_utils.py	Support peft LoRA adapters (#335)	1 year ago