Skip to content

Add B300 config: dsr1-fp4-sglang (non-MTP) #1049

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
functionstackx merged 4 commits into from
Apr 17, 2026
+118 −1

Gate B300 MODEL path override to Qwen3.5-397B-A17B-FP8 only

20dbe26
Select commit
Loading
Failed to load commit list.
Merged

Add B300 config: dsr1-fp4-sglang (non-MTP) #1049

Gate B300 MODEL path override to Qwen3.5-397B-A17B-FP8 only
20dbe26
Select commit
Loading
Failed to load commit list.
Claude / Claude Code Review completed Apr 17, 2026 in 14m 55s

Code review found 1 important issue

Found 5 candidates, confirmed 1. See review comments for details.

Details

Severity Count
🔴 Important 1
🟡 Nit 0
🟣 Pre-existing 0
Severity File:Line Issue
🔴 Important runners/launch_b300-nv.sh:219-227 DSR1 FP4 B300: MODEL not rewritten to local path, benchmark will fail

Annotations

Check failure on line 227 in runners/launch_b300-nv.sh

See this annotation in the file changed.

@claude claude / Claude Code Review

DSR1 FP4 B300: MODEL not rewritten to local path, benchmark will fail 

The MODEL path rewrite in launch_b300-nv.sh was narrowed to only apply to Qwen/Qwen3.5-397B-A17B-FP8; for the new dsr1-fp4-b300-sglang config (model: nvidia/DeepSeek-R1-0528-FP4-V2), MODEL is never rewritten and remains the HuggingFace repo ID. Inside the B300 single-node container, HF_HUB_CACHE=/mnt/hf_hub_cache/ (set by CI) is exported via --export=ALL but /mnt/hf_hub_cache/ is never mounted — only /scratch/models:/scratch/models is mounted — so hf download nvidia/DeepSeek-R1-0528-FP4-V2 canno
View more details on Claude