From 9b2f7f8a91d426b51bb78fe1360541a629e08565 Mon Sep 17 00:00:00 2001 From: zijiexia <37504505+zijiexia@users.noreply.github.com> Date: Thu, 23 Apr 2026 12:01:58 -0700 Subject: [PATCH] docs: split MI300X and MI325X options in GLM-5.1 generator (#23540) Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --- docs_new/cookbook/autoregressive/intro.mdx | 2 +- docs_new/docs.json | 16 ++++++++-------- .../autoregressive/glm-51-deployment.jsx | 10 ++++++---- 3 files changed, 15 insertions(+), 13 deletions(-) diff --git a/docs_new/cookbook/autoregressive/intro.mdx b/docs_new/cookbook/autoregressive/intro.mdx index 896a8f563..513c30367 100644 --- a/docs_new/cookbook/autoregressive/intro.mdx +++ b/docs_new/cookbook/autoregressive/intro.mdx @@ -28,7 +28,7 @@ metatags: { { id: 'b200', label: 'B200', default: false }, { id: 'gb300', label: 'GB300', default: false }, { id: 'h100', label: 'H100', default: false }, - { id: 'mi300x', label: 'MI300X/MI325X', default: false }, + { id: 'mi300x', label: 'MI300X', default: false }, + { id: 'mi325x', label: 'MI325X', default: false }, { id: 'mi355x', label: 'MI355X', default: false } ] }, @@ -23,7 +24,7 @@ export const GLM51Deployment = () => { title: 'Quantization', getDynamicItems: (values) => { const hw = values.hardware; - const isAMD = hw === 'mi300x' || hw === 'mi355x'; + const isAMD = ['mi300x', 'mi325x', 'mi355x'].includes(hw); const isGB300 = hw === 'gb300'; return [ { id: 'bf16', label: 'BF16', subtitle: 'Full Weights', default: isAMD, disabled: isGB300, disabledReason: isGB300 ? 'BF16 is not recommended on GB300 for GLM-5.1' : '' }, @@ -58,7 +59,7 @@ export const GLM51Deployment = () => { speculative: { name: 'speculative', title: 'Speculative Decoding', - condition: (values) => values.hardware !== 'mi300x' && values.hardware !== 'mi355x', + condition: (values) => !['mi300x', 'mi325x', 'mi355x'].includes(values.hardware), items: [ { id: 'disabled', label: 'Disabled', default: false }, { id: 'enabled', label: 'Enabled', default: true } @@ -72,6 +73,7 @@ export const GLM51Deployment = () => { b200: { fp8: { tp: 8, mem: 0.9 }, bf16: { tp: 16, mem: 0.9 } }, gb300: { fp8: { tp: 4, mem: 0.9 } }, mi300x: { bf16: { tp: 8, mem: 0.80 } }, + mi325x: { bf16: { tp: 8, mem: 0.80 } }, mi355x: { bf16: { tp: 8, mem: 0.80 } } }; @@ -129,7 +131,7 @@ export const GLM51Deployment = () => { const generateCommand = () => { const { hardware, quantization } = values; - const isAMD = hardware === 'mi300x' || hardware === 'mi355x'; + const isAMD = ['mi300x', 'mi325x', 'mi355x'].includes(hardware); const isGB300 = hardware === 'gb300'; const effectiveQuant = isAMD ? 'bf16' : (isGB300 && quantization === 'bf16' ? 'fp8' : quantization); const suffix = effectiveQuant === 'fp8' ? '-FP8' : '';