All issues

Search results

handle_request() occasionally hangs forever (not a GPU fault) -- confirmed live with py-spy + gdb, no Xid errors

Status: Open.

#181 In NVIDIA/TensorRT-Edge-LLM;

· carterlasalle opened on Aug 16, 2026

Idle scheduler loop retains last request's SamplingParams and re-validates it continuously (~30Hz), driving CPU + memory growth with zero active requests

Status: Open.

#180 In NVIDIA/TensorRT-Edge-LLM;

· carterlasalle opened on Aug 16, 2026

[Bug][Jetson AGX Orin] TensorRT slot.cpp decode assertion on every request after rebuilding at maxBatchSize=1 (fc_h_fusion workaround from #151)

Status: Open.

#179 In NVIDIA/TensorRT-Edge-LLM;

· carterlasalle opened on Aug 15, 2026

[Bug] v0.10.0: prebuilt sm_87 (Jetson Orin) CuteDSL artifact missing fmha_v2_d* kernel modules, breaks all LLM engine builds

Status: Open.

#178 In NVIDIA/TensorRT-Edge-LLM;

· Hi5808 opened on Aug 15, 2026

[BUG] Qwen3-TTS CP-FP8 calibration failed, it mixes text and codec embedding domains

bugSomething isn't workingSomething isn't working

Status: Open.

#175 In NVIDIA/TensorRT-Edge-LLM;

· cyhasuka opened on Aug 13, 2026

CuTe DSL SSD head_dim=80 for Nemotron Mamba prefill on SM80+ (Blackwell D64 slab)

Status: Open.

#174 In NVIDIA/TensorRT-Edge-LLM;

· kkbwilldo opened on Aug 13, 2026

CuTe DSL FMHA head_dim=512 for Gemma4 global prefill on Blackwell (SM100+)

Status: Open.

#173 In NVIDIA/TensorRT-Edge-LLM;

· kkbwilldo opened on Aug 13, 2026

[BUG] ONNX Export fails for Qwen3.5 MTP draft model with 4-bit quantized checkpoint due to unpacked mtp.fc.weight shape mismatch

bugSomething isn't workingSomething isn't working

Status: Open.

#168 In NVIDIA/TensorRT-Edge-LLM;

· fffiore opened on Aug 10, 2026

Exporting Alpamayo-R1-10B fails with AssertionError

bugSomething isn't workingSomething isn't working

Status: Open.

#166 In NVIDIA/TensorRT-Edge-LLM;

· FABallemand opened on Aug 6, 2026

position_embeddings need check valid

bugSomething isn't workingSomething isn't working

Status: Open.

#165 In NVIDIA/TensorRT-Edge-LLM;

· lix19937 opened on Aug 6, 2026

Bug: Garbage / repetitive output on Jetson AGX Thor (SM110) across all quantization formats using CuTe DSL FMHA

bugSomething isn't workingSomething isn't working

Status: Open.

#164 In NVIDIA/TensorRT-Edge-LLM;

· SatishSurya1 opened on Aug 5, 2026

Exporting Qwen2.5-VL AWQ checkpoints fails with KeyError: 'num_heads'

bugSomething isn't workingSomething isn't working

Status: Open.

#163 In NVIDIA/TensorRT-Edge-LLM;

· FABallemand opened on Aug 5, 2026