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.

Alexander Borzunov 8a73b41a42 Make ServerState announcements work better (#93) ... - Before this PR, `ServerState.JOINING` was announced only once. This announcement quickly expires in case of the full-size BLOOM, since loading blocks takes several minutes. This PR fixes it, so `ServerState.JOINING` is announced periodically in a thread until blocks are loaded. - This PR also makes the `Server` class a non-thread, so it runs in the main thread and can catch `KeyboardInterrupt`. This is important, since if we are downloading blocks right now, we need to stop it and send the `ServerState.OFFLINE` message. Note that `ModuleContainer` is still a thread. - (minor) For the sake of readability, I moved the `ModuleContainer.create()` definition, so it is now defined before `Server.__init__()` (this is because `.create()` is invoked first).		2 years ago
..
__init__.py	add quantization script for cpu	2 years ago
config.json	add minimalistic benchmarks	2 years ago
convert_model.py	Reduce vocabulary size in test model, fix bug in routing when overlapped (#45)	2 years ago
deploy_server.sh	integrate mixed-8bit model (#39)	2 years ago
inference_one_block.py	WIP: make DistributedBloom compliant with HF interface	2 years ago
local_server_config_example.cfg	deploy swarm on local & remote machines	2 years ago
remote_server_config_example.cfg	deploy swarm on local & remote machines	2 years ago
run_local_servers.sh	integrate mixed-8bit model (#39)	2 years ago
run_remote_servers.sh	Sequential and parallel forward / backward (#36)	2 years ago
run_server.py	Make ServerState announcements work better (#93)	2 years ago
speed_test.py	Add automated tests (#23)	2 years ago