public-mirrors/Kokoro-FastAPI
1
0
Fork 0
mirror of https://github.com/remsky/Kokoro-FastAPI.git synced 2025-08-05 16:48:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update training notes

Browse source
This commit is contained in:
Kishor Prins 2025-05-02 10:40:55 -07:00
parent 32191c688a
commit 9e330c6089
1 changed files with 5 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
docker/rocm/docker-compose.yml
View file

@ -23,17 +23,16 @@ services:
environment: environment:
- USE_GPU=true - USE_GPU=true
- TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 - TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1
# IMPORTANT: ROCm's MIOpen librar will be slow if it has to figure out the optimal kernel shapes for each model # IMPORTANT: ROCm's MIOpen libray will be slow if it has to figure out the optimal kernel shapes for each model
# See documentation on performancing tuning: https://github.com/ROCm/MIOpen/blob/develop/docs/conceptual/tuningdb.rst # See documentation on performancing tuning: https://github.com/ROCm/MIOpen/blob/develop/docs/conceptual/tuningdb.rst
# The volumes above cache the MIOpen shape files and user database for subsequent runs # The volumes above cache the MIOpen shape files and user database for subsequent runs
# #
# Steps: # Steps:
# 1. Run Kokoro once with the following environment variables set: # 1. Run Kokoro once with the following environment variables set:
# - MIOPEN_ENABLE_LOGGING=1 # - MIOPEN_FIND_MODE=3
# - MIOPEN_ENABLE_LOGGING_CMD=1 # - MIOPEN_FIND_ENFORCE=3
# - MIOPEN_LOG_LEVEL=6
# 2. Generate various recordings using sample data (e.g. first couple paragraphs of Dracula); this will be slow # 2. Generate various recordings using sample data (e.g. first couple paragraphs of Dracula); this will be slow
# 3. Comment out the previously set environment variables # 3. Comment out/remove the previously set environment variables
# 4. Add the following environment variables to enable caching of model shapes: # 4. Add the following environment variables to enable caching of model shapes:
# - MIOPEN_ENABLE_LOGGING=0- MIOPEN_FIND_MODE=2 # - MIOPEN_FIND_MODE=2
# 5. Restart the container and run Kokoro again, it should be much faster # 5. Restart the container and run Kokoro again, it should be much faster