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 }}
Uh oh!
There was an error while loading.
Please reload this page
.
NVIDIA
/
TensorRT-LLM
Public
Notifications
You must be signed in to change notification settings
Fork
2.7k
Star
14.6k
Code
Issues
577
Pull requests
867
Discussions
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Discussions
Actions
Projects
Security and quality
Insights
[TRTLLM-12123][feat] Add per-iteration request-aggregate counters to InflightBatchingStats
- #13199
#13199
Merged
pcastonguay
merged 19 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
nv-yna:yna/feat/iter-stats-fpm-mvp
nv-yna/TensorRT-LLM:yna/feat/iter-stats-fpm-mvp
Copy head branch name to clipboard
Apr 27, 2026
Conversation
Commits
19
(19)
Checks
Files changed
Merged
[TRTLLM-12123][feat] Add per-iteration request-aggregate counters to InflightBatchingStats
#13199
pcastonguay
merged 19 commits into
NVIDIA:main
NVIDIA/TensorRT-LLM:main
from
nv-yna:yna/feat/iter-stats-fpm-mvp
nv-yna/TensorRT-LLM:yna/feat/iter-stats-fpm-mvp
Copy head branch name to clipboard
Commits
Commits on Apr 17, 2026
[None][feat] Expose flat ForwardPassMetrics fields on IterationStats
Show description for 086f692
nv-yna
committed
086f692
View commit details
Copy full SHA for 086f692
Browse repository at this point
[None][style] apply pre-commit formatting to FPM fields
Show description for 44d2d80
nv-yna
committed
44d2d80
View commit details
Copy full SHA for 44d2d80
Browse repository at this point
[None][fix] FPM populate: use py_last_context_chunk + iter_states
Show description for c30121b
nv-yna
committed
c30121b
View commit details
Copy full SHA for c30121b
Browse repository at this point
Commits on Apr 20, 2026
[None][chore] Drop attention-DP delivery path from FPM MVP; align unit tests with real populate
Show description for 95530e8
nv-yna
committed
95530e8
View commit details
Copy full SHA for 95530e8
Browse repository at this point
[None][style] apply pre-commit ruff-format + docstring fix
Show description for f0ccf02
nv-yna
committed
f0ccf02
View commit details
Copy full SHA for f0ccf02
Browse repository at this point
[None][test] Cover all 9 FPM camelCase keys in to_json_str round-trip
Show description for dba1627
nv-yna
committed
dba1627
View commit details
Copy full SHA for dba1627
Browse repository at this point
[None][test] Exercise real _update_iter_stats and get_stats pipeline for FPM fields
Show description for 59271f0
nv-yna
committed
59271f0
View commit details
Copy full SHA for 59271f0
Browse repository at this point
[None][fix] Compute scheduledSumPrefillTokens from scheduled_batch (overlap-safe)
Show description for 0730d56
nv-yna
committed
0730d56
View commit details
Copy full SHA for 0730d56
Browse repository at this point
Commits on Apr 21, 2026
[None][chore] Align IterationStats flat counters with sibling-field conventions
Show description for 9bd9133
nv-yna
committed
9bd9133
View commit details
Copy full SHA for 9bd9133
Browse repository at this point
[None][refactor] Move FPM-consumable fields into InflightBatchingStats
Show description for ef81c4f
nv-yna
committed
ef81c4f
View commit details
Copy full SHA for ef81c4f
Browse repository at this point
[None][style] apply pre-commit formatting to reorganization commit
Show description for 963a3f7
nv-yna
committed
963a3f7
View commit details
Copy full SHA for 963a3f7
Browse repository at this point
[None][chore] Fine-tune FPM populate comments and call-site
Show description for 98cce31
nv-yna
committed
98cce31
View commit details
Copy full SHA for 98cce31
Browse repository at this point
[None][chore] Rename test_iter_stats_fpm_fields.py to test_iter_stats_populate.py
Show description for 5bd0867
nv-yna
committed
5bd0867
View commit details
Copy full SHA for 5bd0867
Browse repository at this point
[None][refactor] Rename numCtxPrecomputedTokens to numCtxKvTokens
Show description for c05da0c
nv-yna
committed
c05da0c
View commit details
Copy full SHA for c05da0c
Browse repository at this point
Commits on Apr 23, 2026
[TRTLLM-12123][chore] Add TODO tracking attention-DP per-rank IterationStats
Show description for 8f43e6f
nv-yna
committed
8f43e6f
View commit details
Copy full SHA for 8f43e6f
Browse repository at this point
[TRTLLM-12123][test] Assert pad_batch strips cudagraph dummies on exit
Show description for 629420f
nv-yna
committed
629420f
View commit details
Copy full SHA for 629420f
Browse repository at this point
[TRTLLM-12123][chore] Drop volatile line-number and FPM refs from test comments
Show description for 3ada065
nv-yna
committed
3ada065
View commit details
Copy full SHA for 3ada065
Browse repository at this point
[TRTLLM-12123][chore] Tighten queued-context loop: symmetric counters, narrow except, warn on drift
Show description for 185d075
nv-yna
committed
185d075
View commit details
Copy full SHA for 185d075
Browse repository at this point
Commits on Apr 24, 2026
[TRTLLM-12123][feat] Route queued generation-only requests to dedicated InflightBatchingStats fields
Show description for 4995f8f
nv-yna
committed
4995f8f
View commit details
Copy full SHA for 4995f8f
Browse repository at this point
You can’t perform that action at this time.
