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 }}
codewithdark-git
/
QuantLLM
Public
Uh oh!
There was an error while loading.
Please reload this page
.
Notifications
You must be signed in to change notification settings
Fork
2
Star
17
Code
Issues
0
Pull requests
0
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
Commits
Branch selector
main
User selector
All users
Datepicker
All time
Commit history
Commits on Aug 4, 2026
remove the modal test
codewithdark-git
committed
b7bd7ba
View commit details
Copy full SHA for b7bd7ba
Browse repository at this point
feat: update mypy configuration and add type hints across the codebase
codewithdark-git
committed
b551468
View commit details
Copy full SHA for b551468
Browse repository at this point
feat: add bitsandbytes dependency to CI workflow
codewithdark-git
committed
5d7da93
View commit details
Copy full SHA for 5d7da93
Browse repository at this point
feat: add modal_custom_workflow.py to .gitignore
codewithdark-git
committed
709681c
View commit details
Copy full SHA for 709681c
Browse repository at this point
feat: add CLAUDE.md for project guidance and enhance README with custom workflow and HQQ performance details
codewithdark-git
committed
0688b07
View commit details
Copy full SHA for 0688b07
Browse repository at this point
feat: add end-to-end integration tests for QuantLLM on Modal.com GPUs and enhance model registry tests
codewithdark-git
committed
b51ccd3
View commit details
Copy full SHA for b51ccd3
Browse repository at this point
feat: add verbose flag to command-line interface and update memory tracker output format
codewithdark-git
committed
246a87a
View commit details
Copy full SHA for 246a87a
Browse repository at this point
feat: enhance HQQLinear quantization logic and preserve input dtype in forward pass
codewithdark-git
committed
1c3c1a6
View commit details
Copy full SHA for 1c3c1a6
Browse repository at this point
feat: update model saving and pushing headers with new icons and formatting
codewithdark-git
committed
3fde5df
View commit details
Copy full SHA for 3fde5df
Browse repository at this point
feat: add token support for model loading and enhance dtype inference in SmartConfig
codewithdark-git
committed
57ffb14
View commit details
Copy full SHA for 57ffb14
Browse repository at this point
feat: enhance model loading with optional token support and improve hardware profiling output
codewithdark-git
committed
b83ae03
View commit details
Copy full SHA for b83ae03
Browse repository at this point
feat: enhance BenchmarkResult with dictionary-like access and improve run_benchmark_cli for model handling
codewithdark-git
committed
18fb3a7
View commit details
Copy full SHA for 18fb3a7
Browse repository at this point
feat: add metadata attributes and improve model fetching in registry
codewithdark-git
committed
c780b1e
View commit details
Copy full SHA for c780b1e
Browse repository at this point
Commits on Jul 31, 2026
fix: resolve CI lint and type check failures
Show description for 9bca62c
codewithdark-git
and
MonkeyCode-AI
committed
9bca62c
View commit details
Copy full SHA for 9bca62c
Browse repository at this point
Commits on Jul 30, 2026
docs: add runnable examples, rewrite README, update changelog
Show description for 254d7dd
codewithdark-git
and
MonkeyCode-AI
committed
254d7dd
View commit details
Copy full SHA for 254d7dd
Browse repository at this point
test: comprehensive tests for HQQ, server, benchmark, registry, CLI, CPU kernels
Show description for 5eeb630
codewithdark-git
and
MonkeyCode-AI
committed
5eeb630
View commit details
Copy full SHA for 5eeb630
Browse repository at this point
feat: expand CLI with 9 subcommands, SmartConfig print_summary, version bump
Show description for 1b615d0
codewithdark-git
and
MonkeyCode-AI
committed
1b615d0
View commit details
Copy full SHA for 1b615d0
Browse repository at this point
refactor: replace rich logging with production stdlib logging system
Show description for 0f4ba8a
codewithdark-git
and
MonkeyCode-AI
committed
0f4ba8a
View commit details
Copy full SHA for 0f4ba8a
Browse repository at this point
feat: dynamic model registry with HF Hub integration
Show description for 80a5bbe
codewithdark-git
and
MonkeyCode-AI
committed
80a5bbe
View commit details
Copy full SHA for 80a5bbe
Browse repository at this point
feat: benchmark suite and hardware auto-benchmark
Show description for a9d7614
codewithdark-git
and
MonkeyCode-AI
committed
a9d7614
View commit details
Copy full SHA for a9d7614
Browse repository at this point
feat: OpenAI-compatible inference server
Show description for c72378e
codewithdark-git
and
MonkeyCode-AI
committed
c72378e
View commit details
Copy full SHA for c72378e
Browse repository at this point
feat: CPU INT4/INT8 quantized matmul kernels
Show description for faf3f71
codewithdark-git
and
MonkeyCode-AI
committed
faf3f71
View commit details
Copy full SHA for faf3f71
Browse repository at this point
feat: HQQ native quantization (2-8 bit)
Show description for 5ffa30e
codewithdark-git
and
MonkeyCode-AI
committed
5ffa30e
View commit details
Copy full SHA for 5ffa30e
Browse repository at this point
Commits on Jul 29, 2026
release: v2.1.0 — promote from rc1 to stable
Show description for 299c570
codewithdark-git
and
MonkeyCode-AI
committed
299c570
View commit details
Copy full SHA for 299c570
Browse repository at this point
Commits on Jul 28, 2026
fix: disable mypy warn_unused_ignores for CI compatibility
Show description for d026315
codewithdark-git
and
MonkeyCode-AI
committed
d026315
View commit details
Copy full SHA for d026315
Browse repository at this point
fix: resolve all 145 mypy type errors for CI green build
Show description for 77756ef
codewithdark-git
and
MonkeyCode-AI
committed
77756ef
View commit details
Copy full SHA for 77756ef
Browse repository at this point
ci: fix CI failures for lint (ruff format docs) and mypy (non-blocking)
Show description for feeab60
codewithdark-git
and
MonkeyCode-AI
committed
feeab60
View commit details
Copy full SHA for feeab60
Browse repository at this point
fix: update test mock targets from turbo_model to model_loader module
Show description for fac40e3
codewithdark-git
and
MonkeyCode-AI
committed
fac40e3
View commit details
Copy full SHA for fac40e3
Browse repository at this point
style: apply ruff format across entire codebase
Show description for 24d9e41
codewithdark-git
and
MonkeyCode-AI
committed
24d9e41
View commit details
Copy full SHA for 24d9e41
Browse repository at this point
feat: add list_available_formats, add generation test suite
Show description for dcb0428
codewithdark-git
and
MonkeyCode-AI
committed
dcb0428
View commit details
Copy full SHA for dcb0428
Browse repository at this point
chore: complete PEP 621 migration, add mypy + ruff format to CI
Show description for b62760b
codewithdark-git
and
MonkeyCode-AI
committed
b62760b
View commit details
Copy full SHA for b62760b
Browse repository at this point
refactor: split turbo_model.py into domain-specific mixins
Show description for 443ce37
codewithdark-git
and
MonkeyCode-AI
committed
443ce37
View commit details
Copy full SHA for 443ce37
Browse repository at this point
fix: resolve dependency conflicts and fix trust_remote_code default
Show description for 734a97d
codewithdark-git
and
MonkeyCode-AI
committed
734a97d
View commit details
Copy full SHA for 734a97d
Browse repository at this point
Commits on Apr 29, 2026
refactor: Remove unused imports and redundant code in TurboModel
codewithdark-git
committed
50c9e5d
View commit details
Copy full SHA for 50c9e5d
Browse repository at this point
Merge remote-tracking branch 'refs/remotes/origin/main'
codewithdark-git
committed
91f051e
View commit details
Copy full SHA for 91f051e
Browse repository at this point
Previous
Next
You can’t perform that action at this time.