Skip to content

Pull requests: NVIDIA/TensorRT-Model-Optimizer

New pull request New
40 Open 185 Closed
40 Open 185 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

Add option to real quantize the model
#473 opened Oct 28, 2025 by ajrasane Loading…
@ajrasane
[OMNIML-2917] export layer config using actual prefix instead of hard…
#470 opened Oct 28, 2025 by shengliangxu • Draft
@shengliangxu
1
[Autocast] Optimize _add_cast runtime
#469 opened Oct 27, 2025 by aboubezari Loading…
1
Add MoE pruning support in Minitron
#467 opened Oct 27, 2025 by JRD971000 • Draft
@JRD971000
1
Add convert_llama3_config_to_decilm_config + unit test
#465 opened Oct 27, 2025 by danielkorzekwa Loading…
9
E2E test for the experimental compress algorithm based on https://arxiv.org/abs/2411.19146
#464 opened Oct 27, 2025 by danielkorzekwa Loading…
40
Feat: Eagle3 HF Online - support nano2-vlm and nano3
#463 opened Oct 25, 2025 by h-guo18 Loading…
@h-guo18
3
[5590225] Fixed regression introduced by PR #364 (FP64-to-FP32 conversion)
#462 opened Oct 24, 2025 by gcunhase Loading…
8
Added exception for warning caused while creating int4 tensor
#461 opened Oct 24, 2025 by hthadicherla Loading…
1
[5597780] Add support for FP16-only custom ops
#460 opened Oct 23, 2025 by gcunhase Loading…
2
Add functional test cases for published checkpoints on HF
#455 opened Oct 21, 2025 by noeyy-mino Loading…
13
Preserve original rope scaling type in export due to transformers library AutoConfig issue
#452 opened Oct 17, 2025 by Edwardf0t1 Loading…
15
[1/2] Registry interface for custom quantization functional backend
#449 opened Oct 17, 2025 by realAsma Loading…
9
[5271050, 5274346][ONNX] Add support for Conv-Act-Pool fusion
#448 opened Oct 17, 2025 by gcunhase Loading…
10
Support MOE Export for Nemotron H
#447 opened Oct 17, 2025 by jenchen13 Loading…
2 tasks done
7
Fix ONNX FP8 scaling
#446 opened Oct 17, 2025 by Darth-Kronos Loading…
2
[OMNIML-2673]Create an example for running diffusion models using auto deploy
#443 opened Oct 16, 2025 by ajrasane • Draft
@ajrasane
3
[OMNIML-2857] Support the DeepSeek V3.2 model
#435 opened Oct 14, 2025 by cjluo-nv Loading…
15
Yeyu/debug paralllel draft
#429 opened Oct 13, 2025 by yeyu-nvidia Loading…
5
[MOD1RCU9-11] add testcasefor example onnx_ptq
#427 opened Oct 13, 2025 by joe0731 • Draft
2
Pattern-based fusion for pre_quant_scale
#421 opened Oct 9, 2025 by meenchen • Draft
@meenchen
3
[4975376][5541172]perplexity and kl-divergence benchmark metrics
#411 opened Oct 8, 2025 by ynankani Loading…
29
[New feature] Add Support For Sparse Attention
#408 opened Oct 7, 2025 by kaix-nv Loading…
20
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
ProTip! Follow long discussions with comments:>50.