fix: resolve VRAM OOM, 2-node garbage output, and topology viz crash#3
Merged
Conversation
VRAM management: - Free model + flush tinygrad allocator cache before topology rebuild - Filter non-layer weights per shard (embed_tokens, norm, lm_head) - Fix tied embedding missing on last shard 2-node inference: - Add .float() on logits in TransformerShard forward_base - Fix TEMPERATURE env var int() → float() Other fixes: - ZeroDivisionError in topology_viz.py during download - Pin tinygrad to HEAD (afe9fcaec) for JIT buffer fix - Add 2-node integration test (test_2node.py) - Save defensive patches for read-only buffer crash
grangec
added a commit
that referenced
this pull request
Jun 27, 2026
) VRAM management: - Free model + flush tinygrad allocator cache before topology rebuild - Filter non-layer weights per shard (embed_tokens, norm, lm_head) - Fix tied embedding missing on last shard 2-node inference: - Add .float() on logits in TransformerShard forward_base - Fix TEMPERATURE env var int() → float() Other fixes: - ZeroDivisionError in topology_viz.py during download - Pin tinygrad to HEAD (afe9fcaec) for JIT buffer fix - Add 2-node integration test (test_2node.py) - Save defensive patches for read-only buffer crash Co-authored-by: grangec <grangec@users.noreply.github.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
VRAM management:
2-node inference:
Other fixes: