Skip to content

Pull requests: NVIDIA/TensorRT-Model-Optimizer

New pull request New
38 Open 165 Closed
38 Open 165 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix ONNX FP8 scaling
#446 opened Oct 17, 2025 by Darth-Kronos Loading…
2
Bump trtllm to 1.2.0rc0.post1 and pytorch to 25.08 for cuda 13
#445 opened Oct 17, 2025 by kevalmorabia97 Loading…
1 task
3
Add SD3.5-medium quantization support in ModelOpt Diffusers example
#444 opened Oct 17, 2025 by vishalpandya1990 Loading…
@vishalpandya1990
4
[OMNIML-2673]Create an example for running diffusion models using auto deploy
#443 opened Oct 16, 2025 by ajrasane • Draft
@ajrasane
3
[POC] registry based interface to TensorQuantizer
#437 opened Oct 14, 2025 by realAsma • Draft
3
[Autocast] Add low precision autocasting support for Resize op
#436 opened Oct 14, 2025 by aboubezari Loading…
15
[OMNIML-2857] Support the DeepSeek V3.2 model
#435 opened Oct 14, 2025 by cjluo-nv Loading…
13
Cleanup mixed precision and gather node layer info mapping
#434 opened Oct 14, 2025 by ynankani Loading…
5
Add example for multinode calibration using FSDP2
#432 opened Oct 13, 2025 by sugunav14 Loading…
2 of 5 tasks
@sugunav14
33
Fix megatron distributed checkpoint metadata pass through
#431 opened Oct 13, 2025 by ChenhanYu Loading…
2
Yeyu/debug paralllel draft
#429 opened Oct 13, 2025 by yeyu-nvidia Loading…
3
[MOD1RCU9-11] add testcasefor example onnx_ptq
#427 opened Oct 13, 2025 by joe0731 • Draft
2
ONNX 1.19 compatibility fix for INT4 quantization
#423 opened Oct 10, 2025 by hthadicherla Loading…
15
Pattern-based fusion for pre_quant_scale
#421 opened Oct 9, 2025 by meenchen • Draft
@meenchen
3
Ensure that the ONNX IR version is the max supported version (10)
#416 opened Oct 9, 2025 by gcunhase Loading…
12
Update onnx ptq test to be single threaded and make it faster
#415 opened Oct 8, 2025 by ajrasane Loading…
@ajrasane
12
[4975376][5541172]perplexity and kl-divergence benchmark metrics
#411 opened Oct 8, 2025 by ynankani Loading…
28
[New feature] Add Support For Sparse Attention
#408 opened Oct 7, 2025 by kaix-nv Loading…
20
Added support for quantizing TEGroupedMLP for megatron-lm
#403 opened Oct 7, 2025 by kinjalpatel27 Loading…
63
Explicitly register real quant gemms
#402 opened Oct 6, 2025 by cjluo-nv Loading…
3
Update ReadMe for torch_quant_to_onnx.py example
#395 opened Sep 30, 2025 by ajrasane Loading…
1
@ajrasane
8
EAGLE parallel draft with auto regression; kv cache in EAGLE training
#391 opened Sep 29, 2025 by yeyu-nvidia Loading…
22
[5545101]: AutoCast: Add options to force include node/op in F16
#386 opened Sep 28, 2025 by galagam Loading…
7
Support kv cache quantization for mcore using bmm_quantizers
#375 opened Sep 25, 2025 by kaix-nv Loading…
15
megatron realquant FP8 WIP
#367 opened Sep 24, 2025 by cjluo-nv • Draft
2
ProTip! What’s not been updated in a month: updated:<2025-09-17.