minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Docs] Add GB300 cells and benchmarks for Qwen3.8-27B (#34863)

Browse Source 
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
zijiexia
2026-08-14 15:42:50 +00:00
committed by GitHub
co-authored by Xinyuan Tong yhyang201 Claude Opus 5
parent 29c6be15a4
commit 70e291b70f
3 changed files with 227 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cookbook/autoregressive/Qwen/Qwen3.8-27B.mdx
+3 -3
View File
@@ -161,9 +161,9 @@ checkpoint's calibration scales automatically.
requires a FlashInfer build whose prefill `plan` accepts `uniform_q_len`
(newer than 0.6.15.post1); otherwise run spec with `--attention-backend triton`.
On DGX Spark the 128GB is unified memory shared with the host CPU, so all
three checkpoints fit; its cells use 8192-token prefill chunks and
`--mem-fraction-static 0.95`. The SM121 recipe is not yet validated on that
platform.
three checkpoints fit; its cells use 8192-token prefill chunks,
`--mem-fraction-static 0.95`, and `--disable-prefill-cuda-graph`. The SM121
recipe is not yet validated on that platform.
- **H200 (SM90)**: BF16 and FP8 only — the card has no FP4 tensor cores, so the
NVFP4 checkpoint's MLP would fall back to the Marlin W4A16 weight-only path
and its cell is greyed out. The H200 recipes use 32768-token prefill chunks