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 }}
FlashML-org
/
FreeToken
Public
Notifications
You must be signed in to change notification settings
Fork
1.4k
Star
14.1k
Code
Issues
209
Pull requests
161
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
All pull requests
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
161
(161)
Closed
117
(117)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
More items
Comfortable display density
Compact display density
feat(rocm): run on RDNA3/RDNA4 with torch 2.14/2.15 and ROCm 7.14/10
#587
·
zhangnju
opened
Oct 1, 2026
·
·
1
refactor(hf): merge an override into the section's own dict, with no fallback
#586
·
YevheniiKotyrlo
opened
Oct 1, 2026
Contributor
·
·
perf(linear): run a single-row bf16 projection as one GEMV
#585
·
YevheniiKotyrlo
opened
Sep 30, 2026
Contributor
·
·
fix(engine): size memory pools against the VRAM other processes leave free on Windows
#583
·
YevheniiKotyrlo
opened
Sep 30, 2026
Contributor
·
·
1
test(quant): skip declined local checkpoints and label cache paths portably
#582
·
YevheniiKotyrlo
opened
Sep 30, 2026
Contributor
·
·
fix(windows): read checkpoints without O_DIRECT, posix_fadvise or PROT_READ
#581
·
YevheniiKotyrlo
opened
Sep 30, 2026
Contributor
·
·
fix(windows): serve over loopback ZMQ and a selector event loop
#580
·
YevheniiKotyrlo
opened
Sep 30, 2026
Contributor
·
·
perf(moe): dequant nvfp4 prefill experts by bit placement and load activations contiguously
#578
·
YevheniiKotyrlo
opened
Sep 30, 2026
Contributor
·
·
feat(kvcache): keep prefill-chunk GDN checkpoints in a pinned host bank
#577
·
skavans
opened
Sep 30, 2026
·
·
1
1
fix(windows): build the extensions and JIT kernels with MSVC
#575
·
YevheniiKotyrlo
opened
Sep 29, 2026
Contributor
·
·
feat(engine): --vram-reserve-mb keeps VRAM free at the largest prefill
#574
·
YevheniiKotyrlo
opened
Sep 29, 2026
Contributor
·
·
fix(server): keep a silent stream alive and notice a client that left
#572
·
YevheniiKotyrlo
opened
Sep 29, 2026
Contributor
·
·
1
fix(ple): strict shard schema/geometry, nofollow + bounded discovery, mutation evidence, and pinned-bank admission/rollback
#565
·
Avicennasis
opened
Sep 29, 2026
·
·
fix(server): do not auto-select qwen3 parser for instruct-2507
#564
·
SanjayS45
opened
Sep 28, 2026
·
·
1
feat(moe): pin hot experts so fp8 qwen3.8-flash-next serves on a 48gb card
#563
·
mmletgo
opened
Sep 28, 2026
·
·
8
fix(engine): charge the attention workspace in moe-cache-auto sizing
#562
·
Cyber-Marty
opened
Sep 28, 2026
·
·
1
fix(kvcache): clone inserted radix keys to release request buffers
#559
·
taking-lying-flat
opened
Sep 27, 2026
Contributor
·
·
feat(server): --api-key flag for bearer token auth on the HTTP API
#558
·
santanu20
opened
Sep 27, 2026
·
·
feat(server): publish cumulative prefill and decode timing on /v1/stats
#553
·
mgeldi
opened
Sep 25, 2026
·
·
1
improve installation success rate with higher timeout and retries
#551
·
jlisbz
opened
Sep 25, 2026
·
·
ci(rocm): add ROCm 10.0.0 Dockerfile and validation workflow
#535
·
LZ-QWQ
opened
Sep 22, 2026
Contributor
·
·
fix(server): clamp /v1/models context_length to the allocated KV pool
#531
·
oscar-investmatic
opened
Sep 20, 2026
·
·
1
fix(sampling): apply presence and frequency penalties
#527
·
taking-lying-flat
opened
Sep 19, 2026
Contributor
·
·
feat(kvcache): host-resident prefix tier for hybrid GDN models (snapshots + KV pages)
#525
·
alvarorsouza-arch
opened
Sep 19, 2026
·
·
1
feat(glm5_next): serve GLM-5.3-Flash with tensor parallelism
#507
·
calvarado2004
opened
Sep 17, 2026
·
·
Previous
1
2
3
4
5
6
7
Next
You can’t perform that action at this time.