tzhouam 36ada0478a add back the sleep time for the stage init to avoid single card conflict ...

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

2025-11-10 15:07:01 +08:00

..

config

Dependency refractored to vLLM v0.11.0

2025-11-04 22:06:41 +08:00

core

fix reviews

2025-11-05 23:26:58 +08:00

distributed

update dirs

2025-09-11 15:56:28 +08:00

engine

Dependency refractored to vLLM v0.11.0

2025-11-04 22:06:41 +08:00

entrypoints

add back the sleep time for the stage init to avoid single card conflict

2025-11-10 15:07:01 +08:00

inputs

Dependency refractored to vLLM v0.11.0

2025-11-04 22:06:41 +08:00

model_executor

Port changes from feat/multi-request-stream (vs main)

2025-11-07 15:48:47 +08:00

sample

update dirs

2025-09-11 15:43:43 +08:00

utils

Initial vLLM-omni repository structure

2025-09-11 14:32:51 +08:00

worker

Enhance error handling and logging in pipeline and stage processing. Added detailed logging for prompt loading failures, file writing issues, and stage shutdown processes. Introduced a new logging utility for orchestrator metrics and streamlined stats handling in the PipelinedOmniLLM class.

2025-11-07 18:05:00 +08:00

__init__.py

Refactor end-to-end inference script and enhance argument parsing. Added support for loading prompts from a .pt file, introduced new command-line arguments for initialization and output handling, and improved error handling for prompt loading. Removed deprecated files related to previous implementations.

2025-11-10 11:58:47 +08:00

outputs.py

Dependency refractored to vLLM v0.11.0

2025-11-04 22:06:41 +08:00

patch.py

Dependency refractored to vLLM v0.11.0

2025-11-04 22:06:41 +08:00

request.py

Dependency refractored to vLLM v0.11.0

2025-11-04 22:06:41 +08:00