-
Notifications
You must be signed in to change notification settings - Fork 549
All issues
Issue creation is restricted in this repository
- #1699 · Trenton-Starkey opened
on Jun 12, 2026 4
Issues
is:issue state:open
is:issue state:open
Search results
- Status: Open.#2209 In NVIDIA/Model-Optimizer;
LUT-B Support
questionHelp is is neededHelp is is neededStatus: Open.#2204 In NVIDIA/Model-Optimizer;megatron_generate drops VLM vision inputs during no-cache decoding
bugSomething isn't workingSomething isn't workingStatus: Open.#2189 In NVIDIA/Model-Optimizer;- Status: Open.#2160 In NVIDIA/Model-Optimizer;
Can
auto_quantcalculate the score forkv-cacheseparately?questionHelp is is neededHelp is is neededStatus: Open.#2158 In NVIDIA/Model-Optimizer;Support MiniMax-H3 Visual VAE quantization in ModelOpt
feature requestNew feature or requestNew feature or requestStatus: Open.#2137 In NVIDIA/Model-Optimizer;fold_weight crashes with AttributeError: 'NoneType' object has no attribute 'data' on Megatron models with tied word embeddings
bugSomething isn't workingSomething isn't workingStatus: Open.#2131 In NVIDIA/Model-Optimizer;# [ONNX][Autotune] Integrated quantization does not preserve AutoTune Q/DQ placement on ViT
bugSomething isn't workingSomething isn't workingStatus: Open.#2123 In NVIDIA/Model-Optimizer;[ONNX PTQ] Support for third-party custom ORT/TRT plugins in static calibration
feature requestNew feature or requestNew feature or requestStatus: Open.#2016 In NVIDIA/Model-Optimizer;Recommended FP8 recipe for Blackwell (B200)? Per-tensor
FP8_DEFAULT_CFGunderperforms BF16 at prefill; NVFP4 much faster. Also: exported FP8 checkpoint has no KVq/k/v_scalebugSomething isn't workingSomething isn't workingStatus: Open.#2015 In NVIDIA/Model-Optimizer;- Status: Open.#2011 In NVIDIA/Model-Optimizer;
- Status: Open.#2002 In NVIDIA/Model-Optimizer;