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
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 }}
saneax
/
LightLLM
Public
forked from
ModelTC/LightLLM
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Commits
Branch selector
main
User selector
All users
Datepicker
All time
Commit history
Commits on Mar 21, 2026
Fp8kv support (#1220)
blueswhen
authored
391d2ea
View commit details
Copy full SHA for 391d2ea
Browse repository at this point
Commits on Mar 20, 2026
feat: refactor cpu cache (#1236)
blueswhen
authored
8cc0095
View commit details
Copy full SHA for 8cc0095
Browse repository at this point
Commits on Mar 19, 2026
fix: use enum comparison for socket family check (#1241)
sufubao
authored
a087340
View commit details
Copy full SHA for a087340
Browse repository at this point
fix kernelcofings. (#1240)
hiworldwzj
authored
c42f9a5
View commit details
Copy full SHA for c42f9a5
Browse repository at this point
fix _block_scaled_block_gemm kernel, remove config class (#1239)
hiworldwzj
authored
b355fe7
View commit details
Copy full SHA for b355fe7
Browse repository at this point
triton support int8kv kv cache. (#1238)
hiworldwzj
authored
a7c925c
View commit details
Copy full SHA for a7c925c
Browse repository at this point
Commits on Mar 18, 2026
Set 5090 not support TMA and fix only audio_server (#1237)
Show description for ec39ea2
WANDY666
and
hiworldwzj
authored
ec39ea2
View commit details
Copy full SHA for ec39ea2
Browse repository at this point
auto set schedule way. (#1235)
hiworldwzj
authored
ff4eaa5
View commit details
Copy full SHA for ff4eaa5
Browse repository at this point
Commits on Mar 16, 2026
openai api: max_tokens -> max_completion_tokens (#1222)
shihaobai
authored
14ba4a6
View commit details
Copy full SHA for 14ba4a6
Browse repository at this point
Commits on Mar 13, 2026
bugfix: fix visual recv batch counter type (#1232)
shihaobai
authored
60c18fe
View commit details
Copy full SHA for 60c18fe
Browse repository at this point
fix llava support. (#1231)
hiworldwzj
authored
89209e0
View commit details
Copy full SHA for 89209e0
Browse repository at this point
add --enable_multimodal_visual --enable_multimodal_audio start args. (#1229)
hiworldwzj
authored
b87186b
View commit details
Copy full SHA for b87186b
Browse repository at this point
Commits on Mar 12, 2026
bugfix: vlm models(language-only part) inference error, without --ena… (#1230)
shihaobai
authored
37b3c0e
View commit details
Copy full SHA for 37b3c0e
Browse repository at this point
fix diverse mode router. (#1228)
hiworldwzj
authored
c7a53f1
View commit details
Copy full SHA for c7a53f1
Browse repository at this point
Commits on Mar 11, 2026
openai api add AudioURL and support chat_template.json (#1225)
Show description for db840a4
WANDY666
and
hiworldwzj
authored
db840a4
View commit details
Copy full SHA for db840a4
Browse repository at this point
Add detail log for debug. (#1226)
hiworldwzj
authored
6392e10
View commit details
Copy full SHA for 6392e10
Browse repository at this point
Commits on Mar 10, 2026
support Deepseek3.2 (#1103)
Show description for de4d40d
5 people
authored
de4d40d
View commit details
Copy full SHA for de4d40d
Browse repository at this point
Commits on Mar 7, 2026
use rpyc in model_rpc.py (#1221)
hiworldwzj
authored
8ed5074
View commit details
Copy full SHA for 8ed5074
Browse repository at this point
Commits on Mar 3, 2026
tune triton-fp8w8a8g64 and triton-fp8w8a8g128 in 4090D (#1216)
WANDY666
authored
f5ee4c3
View commit details
Copy full SHA for f5ee4c3
Browse repository at this point
Commits on Mar 2, 2026
Optimize qwen3 moe (#1207)
Show description for a7d5e95
3 people
authored
a7d5e95
View commit details
Copy full SHA for a7d5e95
Browse repository at this point
tune triton-fp8w8a8g64 and triton-fp8w8a8g128 (#1215)
WANDY666
authored
ef57a56
View commit details
Copy full SHA for ef57a56
Browse repository at this point
Commits on Feb 26, 2026
add triton-fp8w8a8g128 quant type. (#1214)
hiworldwzj
authored
f2ab54e
View commit details
Copy full SHA for f2ab54e
Browse repository at this point
Commits on Feb 9, 2026
feat: replace gunicorn with hypercorn for http2 (h2c) support (#1211)
Show description for a27dfc8
ChieloNewctle
and
WuSiYu
authored
a27dfc8
View commit details
Copy full SHA for a27dfc8
Browse repository at this point
fix: correct typo 'recieved' to 'received' in log messages (#1210)
Show description for e15b056
thecaptain789
authored
e15b056
View commit details
Copy full SHA for e15b056
Browse repository at this point
fix: fix a memleak (#1206)
Show description for 57006d4
3 people
authored
57006d4
View commit details
Copy full SHA for 57006d4
Browse repository at this point
Commits on Feb 6, 2026
fix requirements (#1209)
hiworldwzj
authored
bc07fe1
View commit details
Copy full SHA for bc07fe1
Browse repository at this point
add-qwen3-omni-thinker (#1208)
Show description for 8af3048
4 people
authored
8af3048
View commit details
Copy full SHA for 8af3048
Browse repository at this point
support qkv repeat (#1203)
Show description for a2a61ae
WANDY666
and
wangzaijun
authored
a2a61ae
View commit details
Copy full SHA for a2a61ae
Browse repository at this point
Commits on Feb 4, 2026
fix: fix mem leak (#1201)
Show description for d09bb92
3 people
authored
d09bb92
View commit details
Copy full SHA for d09bb92
Browse repository at this point
Commits on Feb 3, 2026
Merge q,kv (#1199)
Show description for bbdc7ba
WANDY666
and
wangzaijun
authored
bbdc7ba
View commit details
Copy full SHA for bbdc7ba
Browse repository at this point
Commits on Feb 2, 2026
refactor(dockerfile): reorganize Dockerfile management (#1200)
shihaobai
authored
d3397d7
View commit details
Copy full SHA for d3397d7
Browse repository at this point
Commits on Jan 30, 2026
feat(model): Add GLM-4.7-Flash model support (#1188)
Show description for 78cc66a
3 people
authored
78cc66a
View commit details
Copy full SHA for 78cc66a
Browse repository at this point
Commits on Jan 29, 2026
fix (#1197)
hiworldwzj
authored
64b0c27
View commit details
Copy full SHA for 64b0c27
Browse repository at this point
Commits on Jan 28, 2026
add-choose-vit-backend (#1191)
Show description for e756ee6
5 people
authored
e756ee6
View commit details
Copy full SHA for e756ee6
Browse repository at this point
Commits on Jan 27, 2026
refactor: weight refactor, including norm, mm, quantization and embedding (#1193)
Show description for 871ace6
3 people
authored
871ace6
View commit details
Copy full SHA for 871ace6
Browse repository at this point
Previous
Next
You can’t perform that action at this time.