Skip to content

Add B300 config: dsr1-fp8-sglang (non-MTP)#1050

Merged
functionstackx merged 2 commits into
mainfrom
claude/add-dsr1-fp8-b300-sglang
Apr 17, 2026
Merged

Add B300 config: dsr1-fp8-sglang (non-MTP)#1050
functionstackx merged 2 commits into
mainfrom
claude/add-dsr1-fp8-b300-sglang

Fill in PR link for dsr1-fp8-b300-sglang changelog entry

43e2882
Select commit
Loading
Failed to load commit list.
Claude / Claude Code Review completed Apr 17, 2026 in 18m 4s

Code review found 1 important issue

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

Details

Severity Count
🔴 Important 1
🟡 Nit 0
🟣 Pre-existing 0
Severity File:Line Issue
🔴 Important benchmarks/single_node/dsr1_fp8_b300.sh:27-28 dsr1_fp8_b300.sh missing B300 adaptations: --enable-symm-mem and B200-only env vars

Annotations

Check failure on line 28 in benchmarks/single_node/dsr1_fp8_b300.sh

See this annotation in the file changed.

@claude claude / Claude Code Review

dsr1_fp8_b300.sh missing B300 adaptations: --enable-symm-mem and B200-only env vars

dsr1_fp8_b300.sh was copied verbatim from the B200 script and is missing two B300-specific adaptations that will cause suboptimal benchmark throughput on B300 hardware. First, lines 27-28 carry over `SGL_ENABLE_JIT_DEEPGEMM=false` and `SGLANG_ENABLE_FLASHINFER_GEMM=true` from B200 — no other B300 SGLang script sets these, and `SGL_ENABLE_JIT_DEEPGEMM=false` actively disables a JIT GEMM path that all other B300 scripts leave enabled by default. Second, the SGLang server launch (lines 76-80) is mi