-
Notifications
You must be signed in to change notification settings - Fork 2.5k
- #15044 · laikhtewari opened
on Jun 6, 2026 1 - #3148 · juney-nvidia opened
on Mar 29, 2025 5 - #3124 · juney-nvidia opened
on Mar 27, 2025 11
Issues
is:issue state:open
is:issue state:open
Issue creation is restricted in this repository
Search results
[Bug] test_unittests_v2[unittest/_torch/executor] wrapper fails intermittently (~40%) with all inner tests passing — session teardown crash
Pytorch<NV>Pytorch backend related issues<NV>Pytorch backend related issuesTesting<NV>Continuous integration, build system, and testing infrastructure issues<NV>Continuous integration, build system, and testing infrastructure issuesStatus: Open.#16284 In NVIDIA/TensorRT-LLM;[Bug] test_nvfp4_gather_grouped_gemm_act_fusion_blackwell flaky on B300: ~0.05% mismatch vs rtol 1e-4, varying parametrizations
Pytorch<NV>Pytorch backend related issues<NV>Pytorch backend related issuesStatus: Open.#16281 In NVIDIA/TensorRT-LLM;[Bug] test_dflash_qwen3_5_4b flaky-marginal in DGX_H100-PyTorch-5: mean accepted 0.9909 < 1.0, alternating [True]/[False] variants
Speculative Decoding<NV>MTP/Eagle/Medusa/Lookahead/Prompt-Lookup-Decoding/Draft-Target-Model/ReDrafter<NV>MTP/Eagle/Medusa/Lookahead/Prompt-Lookup-Decoding/Draft-Target-Model/ReDrafterTesting<NV>Continuous integration, build system, and testing infrastructure issues<NV>Continuous integration, build system, and testing infrastructure issuesStatus: Open.#16277 In NVIDIA/TensorRT-LLM;[Bug] TestGemma4MoE::test_bf16 fails deterministically in pre-merge DGX_H100-4_GPUs-AutoDeploy-1: Not registered specs (bf16/auto)
AutoDeploy<NV> AutoDeploy Backend<NV> AutoDeploy BackendStatus: Open.#16275 In NVIDIA/TensorRT-LLM;[Feature]: Extend the v1 KV cache manager with a disk (L3) tier and per-request retention
KV-Cache Managementkv-cache management for efficient LLM inferencekv-cache management for efficient LLM inferenceStatus: Open.#16251 In NVIDIA/TensorRT-LLM;[DeepSeek-V4] Loading nvidia/DeepSeek-V4-Pro-NVFP4 crashes: 'Linear' object has no attribute 'weight_scale' in fused_a loader (MIXED_PRECISION attn excluded → built BF16 but stored as FP8)
Customized kernels<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.Model optimization<NV>Model-specific performance optimizations and tuning<NV>Model-specific performance optimizations and tuningStatus: Open.#16196 In NVIDIA/TensorRT-LLM;[Bug]: Gemma4 INT4 AWQ quantization fails during export: Gemma4Config has no attribute vocab_size
bugSomething isn't workingSomething isn't workingCustomized kernels<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.Status: Open.#16171 In NVIDIA/TensorRT-LLM;[Feature]: Expose SmoothQuant alpha for int8_sq quantization in quantize.py
feature requestNew feature or request. This includes new model, dtype, functionality supportNew feature or request. This includes new model, dtype, functionality supportModel optimization<NV>Model-specific performance optimizations and tuning<NV>Model-specific performance optimizations and tuningStatus: Open.#16151 In NVIDIA/TensorRT-LLM;[Bug]: 142 GiB/rank host memory leak (leading to host OOM if KV cache offloading is enabled) when serving Kimi-K2.6-NVFP4 TP4 on GB300 (aarch64), due to MetaInitException on aten.fill_.Scalar (nn.LayerNorm init) silently falling back to whole-model CPU construction
Customized kernels<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.Pytorch<NV>Pytorch backend related issues<NV>Pytorch backend related issuesStatus: Open.#16086 In NVIDIA/TensorRT-LLM;[AutoDeploy]: Migrate btk to support llmc
AutoDeploy/llmc-blocker<NV> Tag for issues that are blocking AutoDeploy standalone repo<NV> Tag for issues that are blocking AutoDeploy standalone repofeature requestNew feature or request. This includes new model, dtype, functionality supportNew feature or request. This includes new model, dtype, functionality supportStatus: Open.#16076 In NVIDIA/TensorRT-LLM;[Bug]: IndexError: tuple index out of range when loading Qwen 3.6 35B during Quantizing
bugSomething isn't workingSomething isn't workingCustomized kernels<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.<NV>Specialized/modified CUDA kernels in TRTLLM for LLM ops, beyond standard TRT. Dev & perf.Status: Open.#16075 In NVIDIA/TensorRT-LLM;[Feature]: Paged / KV-manager-resident storage for the DFlash draft context, replacing the dense buffer
feature requestNew feature or request. This includes new model, dtype, functionality supportNew feature or request. This includes new model, dtype, functionality supportSpeculative Decoding<NV>MTP/Eagle/Medusa/Lookahead/Prompt-Lookup-Decoding/Draft-Target-Model/ReDrafter<NV>MTP/Eagle/Medusa/Lookahead/Prompt-Lookup-Decoding/Draft-Target-Model/ReDrafterStatus: Open.#16005 In NVIDIA/TensorRT-LLM;