Search results

NVFP4 ONNX export fails when rotate=True (FWHT trace + post-processor)

bugSomething isn't workingSomething isn't working

featureIssue in actual ModelOpt featureIssue in actual ModelOpt feature

onnx.quantization

torch.quantization

Status: Open.

#1424 In NVIDIA/Model-Optimizer;

· Clemxxx opened on May 10, 2026

Add VLM components to _default_disabled_quantizer_cfg?

feature requestNew feature or requestNew feature or request

Status: Open.

#1396 In NVIDIA/Model-Optimizer;

· harmya opened on May 6, 2026

Do you have plans to support Qwen Image Edit?

feature requestNew feature or requestNew feature or request

Status: Open.

#1366 In NVIDIA/Model-Optimizer;

· lzcchl opened on Apr 29, 2026

[Feature Request] DeepSeek-V4-Flash & DeepSeek-V4-Pro NVFP4 checkpoint

feature requestNew feature or requestNew feature or request

Status: Open.

#1346 In NVIDIA/Model-Optimizer;

· erhwenkuo opened on Apr 27, 2026

Logical conflict between data loading and collation.

questionHelp is is neededHelp is is needed

Status: Open.

#1319 In NVIDIA/Model-Optimizer;

· wenqibiao opened on Apr 22, 2026

[Feature Request] Kimi-K2.6 NVFP4 checkpoint and corresponding EAGLE3 draft model for offline speculative decoding

feature requestNew feature or requestNew feature or request

Status: Open.

#1308 In NVIDIA/Model-Optimizer;

· dododream opened on Apr 21, 2026

Attention-only LoRA fine-tuning on NVFP4-quantized 122B MoE — community implementation + preprint

questionHelp is is neededHelp is is needed

Status: Open.

#1294 In NVIDIA/Model-Optimizer;

· ddreeselogs opened on Apr 19, 2026

GLM5.1 nvfp4 checkpoint

feature requestNew feature or requestNew feature or request

Status: Open.

#1283 In NVIDIA/Model-Optimizer;

· functionstackx opened on Apr 16, 2026

What’s the Correct Way to Quantize Qwen3.5 (MoE/Dense) to NVFP4?

questionHelp is is neededHelp is is needed

Status: Open.

#1255 In NVIDIA/Model-Optimizer;

· seindum opened on Apr 14, 2026

Pre-Quantized Checkpoints: Gemma 4 models

feature requestNew feature or requestNew feature or request

Status: Open.

#1237 In NVIDIA/Model-Optimizer;

· rnett opened on Apr 11, 2026

Add _QuantGemma4TextExperts plugin for fused 3D MoE expert quantization

feature requestNew feature or requestNew feature or request

torch.quantization

triaged

Status: Open.

#1173 In NVIDIA/Model-Optimizer;

· marioiseli89 opened on Apr 3, 2026

ONNX models generated by llm_export.py are missing some input and output nodes

bugSomething isn't workingSomething isn't working

triaged

Status: Open.

#1147 In NVIDIA/Model-Optimizer;

· idruker-cerence opened on Mar 31, 2026