fix: memory_bytes dtype bug, remove debug logging, cleanup temp files,auto-detect GPUs#9
Open
kunwar-vikrant wants to merge 1 commit into
Open
Conversation
kunwar-vikrant
changed the title
…, auto-detect GPUs - store.py: memory_bytes() now uses tensor.element_size() instead of hardcoded *2, fixing underestimation for float32 tensors - vllm_attn_backend.py: replaced /tmp/tq_debug.log file writes with proper logger.debug()/logger.error() calls - benchmark.py, proof.py: added try/finally to clean up /tmp/tq_*.py temp files after subprocess runs - benchmark.py, proof.py: replaced hardcoded GPU fallback '0,1,4,6' with _default_gpu_ids() auto-detection via torch.cuda.device_count()
kunwar-vikrant
force-pushed
the
fix/cleanup-and-bugfixes
branch
from
5828620 to
3ff1c8e
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.