Skip to content

Navigation Menu

Appearance settings

View all features
View all solutions
- EXPLORE BY TOPIC
  AI
  Software Development
  DevOps
  Security
  View all topics
- EXPLORE BY TYPE
  Customer stories
  Events & webinars
  Ebooks & reports
  Business insights
  GitHub Skills
- SUPPORT & SERVICES
  Documentation
  Customer support
  Community forum
  Trust center
  Partners
View all resources
- ENTERPRISE SOLUTIONS
  Enterprise platformAI-powered developer platform
- AVAILABLE ADD-ONS
  GitHub Advanced SecurityEnterprise-grade security features
  Copilot for BusinessEnterprise-grade AI features
  Premium SupportEnterprise-grade 24/7 support
Pricing

Appearance settings

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

SemiAnalysisAI / InferenceX Public

Notifications You must be signed in to change notification settings
Fork 303
Star 1.7k

Code
Issues 103
Pull requests 192
Discussions
Actions
Projects
Security and quality
Insights

Additional navigation options

Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights

Add B300 Qwen3.5 397B FP8 disaggregated AgentX recipes - #3268

#3268

Open

cquil11 wants to merge 46 commits into

mainSemiAnalysisAI/InferenceX:mainfrom

cam/qwen35-b300-disaggSemiAnalysisAI/InferenceX:cam/qwen35-b300-disaggCopy head branch name to clipboard

Conversation Commits46 (46)Checks Files changed

Open

Add B300 Qwen3.5 397B FP8 disaggregated AgentX recipes#3268
cquil11 wants to merge 46 commits into
mainfrom
cam/qwen35-b300-disagg

Merge remote-tracking branch 'origin/main' into cam/b300-qwen35-selec…

f0b8840

Select commit

Loading

Failed to load commit list.

Uh oh!

There was an error while loading. Please reload this page.

blacksmith.sh

[code]smith

CodeQL - Code Quality on: dynamic 1

Analyze (python)

CI on: pull_request 2

Lint

Tests

Run Sweep on: pull_request 7

check-changelog

reuse-sweep-gate

setup

canary-select

canary /

multi-node 1k1k /

multi-node 8k1k /

single-node 1k1k /

single-node 8k1k /

agentic /

multi-node agentic / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-A17B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4) x 1D (TP4) mtp dram KV offload hicache c8

multi-node agentic / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-A17B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4) x 1D (TP4) mtp dram KV offload hicache c24

multi-node agentic / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-A17B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4/EP4) x 1D (TP4) mtp dram KV offload hicache c32

multi-node agentic / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-A17B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP2/EP2) x 1D (TP2/EP2) mtp dram KV offload hicache c32

multi-node agentic / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-A17B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP2/EP2) x 1D (TP2/EP2) mtp dram KV offload hicache c40

multi-node agentic / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-A17B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4) x 1D (TP4) mtp dram KV offload hicache c40

multi-node agentic / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-A17B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4) x 1D (TP4) mtp dram KV offload hicache c48

eval /

agentic eval /

multi-node eval /

multi-node agentic eval / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4) x 1D (TP4) mtp dram KV offload hicache c8 | eval-only

multi-node agentic eval / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4) x 1D (TP4) mtp dram KV offload hicache c24 | eval-only

multi-node agentic eval / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4/EP4) x 1D (TP4) mtp dram KV offload hicache c32 | eval-only

multi-node agentic eval / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP2/EP2) x 1D (TP2/EP2) mtp dram KV offload hicache c32 | eval-only

multi-node agentic eval / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP2/EP2) x 1D (TP2/EP2) mtp dram KV offload hicache c40 | eval-only

multi-node agentic eval / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4) x 1D (TP4) mtp dram KV offload hicache c40 | eval-only

multi-node agentic eval / (lmsysorg/sglang:nightly-dev-cu13-20260918-20518d85, Qwen/Qwen3.5-397B-... / p0.000 | qwen3.5 fp8 cluster:b300-dsxe dyn-sgl 1P (TP4) x 1D (TP4) mtp dram KV offload hicache c48 | eval-only

Select a check to view from the sidebar

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms
Privacy
Security
Status
Community
Docs
Contact

You can’t perform that action at this time.