Skip to content

[NVIDIA] Disable prefix minimax #966

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Oseltamivir merged 2 commits into from
Mar 28, 2026

perfchangelog

d29b969
Select commit
Loading
Failed to load commit list.
Merged

[NVIDIA] Disable prefix minimax #966

perfchangelog
d29b969
Select commit
Loading
Failed to load commit list.
Claude / Claude Code Review completed Mar 27, 2026 in 9m 32s

Code review found 2 potential issues

Found 2 candidates, confirmed 2. See review comments for details.

Details

Severity Count
🔴 Important 0
🟡 Nit 0
🟣 Pre-existing 1
Severity File:Line Issue
🟣 Pre-existing benchmarks/single_node/minimaxm2.5_fp8_b200.sh:43-49 EP_SIZE condition always enables expert parallel (-ge 1 should be -gt 1)

Annotations

Check notice on line 49 in benchmarks/single_node/minimaxm2.5_fp8_b200.sh

See this annotation in the file changed.

@claude claude / Claude Code Review

EP_SIZE condition always enables expert parallel (-ge 1 should be -gt 1) 

Pre-existing bug in minimaxm2.5_fp8_b200.sh and minimaxm2.5_fp8_h200.sh: the EP_SIZE guard uses -ge 1 instead of -gt 1, making the else branch (which disables expert parallel) completely unreachable. Fix by changing [ "$EP_SIZE" -ge 1 ] to [ "$EP_SIZE" -gt 1 ] in both scripts, matching the pattern already used in h100.sh and mi355x.sh.
View more details on Claude