[None][fix] configure DeepGEMM PDL during engine init#15004
Conversation
Signed-off-by: Jin Li <59594262+liji-nv@users.noreply.github.com>
liji-nv
requested review from
achartier and
yizhang-nv
and removed request for
a team
|
/bot run --disable-fail-fast --add-multi-gpu-tests |
|
PR_Github #52341 Bot args parsing error: usage: /bot [-h] |
|
/bot run |
|
PR_Github #52362 [ run ] triggered by Bot. Commit: |
|
PR_Github #52362 [ run ] completed with state
|
|
|
||
| from tensorrt_llm import deep_gemm | ||
|
|
||
| deep_gemm.set_pdl(os.environ.get("TRTLLM_ENABLE_PDL", "1") == "1") |
There was a problem hiding this comment.
We could re-use get_env_enable_pdl from flashinfer_utils.py here.
|
|
||
| def _configure_deep_gemm_pdl() -> None: | ||
| global _DEEP_GEMM_PDL_CONFIGURED | ||
| if _DEEP_GEMM_PDL_CONFIGURED: |
There was a problem hiding this comment.
I'm not sure if the check is really useful since that function is called from __init__, so it should only be called once. If it was called from multiple places, we should have proper locking anyway.
4 participants
@coderabbitai summary
Description
Test Coverage
PR Checklist
Please review the following before submitting your PR:
PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.
PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.
Test cases are provided for new code paths (see test instructions)
If PR introduces API changes, an appropriate PR label is added - either
api-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin the PR title.Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
Update tava architecture diagram if there is a significant design change in PR.
The reviewers assigned automatically/manually are appropriate for the PR.
Please check this after reviewing the above items as appropriate for this PR.
GitHub Bot Help
To see a list of available CI bot commands, please comment
/bot help.