FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[Original HTTPS Page]
Issues · NVIDIA/Model-Optimizer · GitHub
Uh oh!
There was an error while loading.
Please reload this page
.
NVIDIA
/
Model-Optimizer
Public
Notifications
You must be signed in to change notification settings
Fork
559
Star
3.6k
Code
Issues
92
Pull requests
280
Actions
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Security and quality
Insights
Issues
Assigned to me
Created by me
Mentioned
Recent activity
Views
Milestones
Labels
All issues
Issue creation is restricted in this repository
[RFC] NVIDIA Model Optimizer — Product Roadmap
#1699 ·
Trenton-Starkey
opened
on Jun 12, 2026
4
Issues
Search Issues
is
:
issue
state
:
open
is:issue state:open
Search
Search results
Open
Closed
ONNX PTQ: no NVFP4 path for convolutional models
Status: Open.
#2281
In NVIDIA/Model-Optimizer;
·
geoffrey-delhomme
opened
on Aug 28, 2026
hf_ptq.py: deprecated --auto_quantize_bits CLI flag silently no-ops instead of enabling AutoQuantize
Status: Open.
#2230
In NVIDIA/Model-Optimizer;
·
wyattearp
opened
on Aug 22, 2026
[Feature Request] DeepSeek-V4-Flash-0731 NVFP4 checkpoint
feature request
New feature or request
New feature or request
Status: Open.
#2220
In NVIDIA/Model-Optimizer;
·
nicole-lihui
opened
on Aug 20, 2026
Per-expert weight_quantizer._amax fails Megatron validate_sharding_integrity on topology reshard (TEGroupedMLP NVFP4)
Status: Open.
#2209
In NVIDIA/Model-Optimizer;
·
kevalmorabia97
opened
on Aug 18, 2026
LUT-B Support
question
Help is is needed
Help is is needed
Status: Open.
#2204
In NVIDIA/Model-Optimizer;
·
brian-dellabetta
opened
on Aug 17, 2026
megatron_generate drops VLM vision inputs during no-cache decoding
bug
Something isn't working
Something isn't working
Status: Open.
#2189
In NVIDIA/Model-Optimizer;
·
cuichenx
opened
on Aug 13, 2026
[Bug] init_quantized_weights / --low_memory_mode exports numerically broken NVFP4 (quantizes meta tensors before weights load)
Status: Open.
#2160
In NVIDIA/Model-Optimizer;
·
spped2000
opened
on Aug 12, 2026
Can auto_quant calculate the score for kv-cache separately?
question
Help is is needed
Help is is needed
Status: Open.
#2158
In NVIDIA/Model-Optimizer;
·
zcfh
opened
on Aug 12, 2026
Support MiniMax-H3 Visual VAE quantization in ModelOpt
feature request
New feature or request
New feature or request
Status: Open.
#2137
In NVIDIA/Model-Optimizer;
·
baonudesifeizhai
opened
on Aug 10, 2026
# [ONNX][Autotune] Integrated quantization does not preserve AutoTune Q/DQ placement on ViT
bug
Something isn't working
Something isn't working
Status: Open.
#2123
In NVIDIA/Model-Optimizer;
·
HannisLee
opened
on Aug 10, 2026
[ONNX PTQ] Support for third-party custom ORT/TRT plugins in static calibration
feature request
New feature or request
New feature or request
Status: Open.
#2016
In NVIDIA/Model-Optimizer;
·
e-said
opened
on Jul 24, 2026
Recommended FP8 recipe for Blackwell (B200)? Per-tensor FP8_DEFAULT_CFG underperforms BF16 at prefill; NVFP4 much faster. Also: exported FP8 checkpoint has no KV q/k/v_scale
bug
Something isn't working
Something isn't working
Status: Open.
#2015
In NVIDIA/Model-Optimizer;
·
Francesco-Carlucci
opened
on Jul 24, 2026
Back
|
FazBrowse Home
|
New Git URL