mirror/OpenLLM
1
0
Fork 0
mirror of https://github.com/bentoml/OpenLLM.git synced 2026-01-17 11:58:07 -05:00
Code Issues Packages Projects Releases Wiki Activity

perf(build): locking and improve build speed (#669)

Browse Source 
* revert(build): not locking packages

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* perf: improve svars generation and unifying envvar parsing

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* docs: update changelog

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

* chore: update stubs check for mypy

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>

---------

Signed-off-by: Aaron Pham <29749331+aarnphm@users.noreply.github.com>
This commit is contained in:
Aaron Pham
2023-11-16 06:27:45 -05:00
committed by GitHub
parent fce8f223f3
commit 8fdfd0491f
9 changed files with 138 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
openllm-python/src/openllm_cli/entrypoint.py
View File

@@ -622,9 +622,22 @@ def start_grpc_command(
def process_environ(
config, server_timeout, wpr, device, cors, model_id, adapter_map, serialisation, llm, system_message, prompt_template
config,
server_timeout,
wpr,
device,
cors,
model_id,
adapter_map,
serialisation,
llm,
system_message,
prompt_template,
use_current_env=True,
) -> t.Dict[str, t.Any]:
environ = parse_config_options(config, server_timeout, wpr, device, cors, os.environ.copy())
environ = parse_config_options(
config, server_timeout, wpr, device, cors, os.environ.copy() if use_current_env else {}
)
environ.update(
{
'OPENLLM_MODEL_ID': model_id,
@@ -1019,22 +1032,21 @@ def build_command(
),
)
backend_warning(llm.__llm_backend__, build=True)
os.environ.update(
{
'TORCH_DTYPE': dtype,
'OPENLLM_BACKEND': llm.__llm_backend__,
'OPENLLM_SERIALIZATION': llm._serialisation,
'OPENLLM_MODEL_ID': llm.model_id,
'OPENLLM_ADAPTER_MAP': orjson.dumps(None).decode(),
}
**process_environ(
llm.config,
llm.config['timeout'],
1.0,
None,
True,
llm.model_id,
None,
llm._serialisation,
llm,
llm._system_message,
llm._prompt_template,
)
)
if llm.quantise:
os.environ['OPENLLM_QUANTIZE'] = str(llm.quantise)
if system_message:
os.environ['OPENLLM_SYSTEM_MESSAGE'] = system_message
if prompt_template:
os.environ['OPENLLM_PROMPT_TEMPLATE'] = prompt_template
try:
assert llm.bentomodel # HACK: call it here to patch correct tag with revision and everything
@@ -1049,7 +1061,7 @@ def build_command(
llm_fs.writetext('Dockerfile.template', dockerfile_template.read())
dockerfile_template_path = llm_fs.getsyspath('/Dockerfile.template')
adapter_map: dict[str, str] | None = None
adapter_map = None
if adapter_id and not build_ctx:
ctx.fail("'build_ctx' is required when '--adapter-id' is passsed.")
if adapter_id: