Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
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
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
Accelerator
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Search
/
Sign in
Sign up
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
{{ message }}
Uh oh!
There was an error while loading.
Please reload this page
.
SemiAnalysisAI
/
InferenceX
Public
Notifications
You must be signed in to change notification settings
Fork
257
Star
1.4k
Code
Issues
103
Pull requests
104
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
[NV] Add SpeedBench AL collectors for DSV4-Pro-0813 on B300
- #2526
#2526
Merged
cquil11
merged 7 commits into
main
SemiAnalysisAI/InferenceX:main
from
albecheng/speedbench-al-dsv4-dspark
SemiAnalysisAI/InferenceX:albecheng/speedbench-al-dsv4-dspark
Copy head branch name to clipboard
Aug 14, 2026
Conversation
Commits
7
(7)
Checks
Files changed
Merged
[NV] Add SpeedBench AL collectors for DSV4-Pro-0813 on B300
#2526
cquil11
merged 7 commits into
main
SemiAnalysisAI/InferenceX:main
from
albecheng/speedbench-al-dsv4-dspark
SemiAnalysisAI/InferenceX:albecheng/speedbench-al-dsv4-dspark
Copy head branch name to clipboard
Commits
Commits on Aug 7, 2026
[NV] Add SpeedBench AL collectors for DSV4-Pro DSpark on B300
Show description for a472c84
qiching
committed
a472c84
View commit details
Copy full SHA for a472c84
Browse repository at this point
Download the DSpark checkpoint instead of expecting it staged; batch the pass
Show description for eb9c2c2
qiching
committed
eb9c2c2
View commit details
Copy full SHA for eb9c2c2
Browse repository at this point
Probe for native --chat-template-kwargs instead of always patching
Show description for b60e95d
qiching
committed
b60e95d
View commit details
Copy full SHA for b60e95d
Browse repository at this point
Assert native --chat-template-kwargs support instead of patching for it
Show description for b6cca89
qiching
committed
b6cca89
View commit details
Copy full SHA for b6cca89
Browse repository at this point
Cap max_num_seqs so DSpark cells past 3 tokens fit, and survive a dead cell
Show description for 119551e
qiching
committed
119551e
View commit details
Copy full SHA for 119551e
Browse repository at this point
Follow the published B300 DSpark recipe: expert parallel + deep_gemm_mega_moe
Show description for f3a5ae2
qiching
committed
f3a5ae2
View commit details
Copy full SHA for f3a5ae2
Browse repository at this point
Commits on Aug 14, 2026
Read staged DeepSeek-V4-Pro-0813 from the read-only mount
Show description for 6162a13
qiching
committed
6162a13
View commit details
Copy full SHA for 6162a13
Browse repository at this point
You can’t perform that action at this time.