Skip to content

docs(qwen3): add 14B and GH200 family benchmarks #13

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
xiaguan merged 4 commits into from
Aug 24, 2026
Merged

docs(qwen3): add 14B and GH200 family benchmarks #13

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
96df3a4
docs(qwen3): add 14B and GH200 family benchmarks
FeathBow Jul 17, 2026
b46bb02
docs(qwen3): add 0.6B and 1.7B verification
FeathBow Aug 21, 2026
d13b5f3
docs(qwen3): fix table overflow and level the GH200 summary
FeathBow Aug 21, 2026
8197bea
Merge remote-tracking branch 'origin/main' into mira/review-pr13-resolve
xiaguan Aug 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion astro.config.mjs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,7 +118,7 @@ export default defineConfig({
{
label: 'Models',
items: [
{ label: 'Qwen3-4B / 8B / 32B', link: '/models/qwen3-4b/' },
{ label: 'Qwen3 Dense', link: '/models/qwen3-4b/' },
{ label: 'Qwen3.5 Dense', link: '/models/qwen35/' },
{ label: 'GLM-5.2', link: '/models/glm52/' },
{ label: 'Gemma 4 12B', link: '/models/gemma4/' },
Expand Down
2 changes: 1 addition & 1 deletion src/content/docs/index.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ Decode is captured as a CUDA graph with pre-allocated buffers, keeping per-token

| Model | Architecture |
| --- | --- |
| [Qwen3-4B / 8B / 32B](/models/qwen3-4b/) | Full attention, tensor parallel |
| [Qwen3 Dense](/models/qwen3-4b/) | Full attention, tensor parallel |
| [Qwen3.5 Dense](/models/qwen35/) | Hybrid: 3:1 linear + full attention layers |
| DeepSeek-V4 | MoE + compressor + indexer, 8-GPU |
| DeepSeek-V2-Lite | MoE + expert parallelism, 2-GPU |
Expand Down
Loading