Skip to content

Pull requests: NVIDIA/TensorRT-Edge-LLM

New pull request New
16 Open 29 Closed
16 Open 29 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

fix(checkpoint): Preserve destination tensor dtype
#149 opened Jul 25, 2026 by suharvest Loading…
1
fix(attention): Scope FMHA cubin loading by mask type
#148 opened Jul 25, 2026 by suharvest Loading…
1
fix: Support stream readers before TensorRT 10.7
#147 opened Jul 25, 2026 by suharvest Loading…
1
fix: Normalize ASR MRoPE metadata for runtime
#146 opened Jul 25, 2026 by suharvest Loading…
1
fix: Guard FP4 data type before TensorRT 10.8
#145 opened Jul 25, 2026 by suharvest Loading…
1
Cosmos
#135 opened Jul 22, 2026 by micwill755 • Draft
5 of 7 tasks
1
feat(builder): Set workspace RAM limits and enhance log level controls
#126 opened Jul 6, 2026 by cjac Loading…
7 tasks done
Fix SM110 NVFP4 MoE CuteDSL runner build
#124 opened Jul 4, 2026 by whitesscott Loading…
Strip /usr/include from apt pybind11's interface include dirs
#121 opened Jul 2, 2026 by whitesscott Loading…
4 tasks
Use <cmath> instead of <math.h> in context attention FMHA headers
#120 opened Jul 1, 2026 by whitesscott Loading…
3 tasks
fix: Respect native Orin CUDA architecture and CuTe link requirements
#118 opened Jun 28, 2026 by suharvest Loading…
1
1
fix: propagate CuTe DSL runtime link requirements for static libraries
#103 opened Jun 7, 2026 by francismelon Loading…
3 of 7 tasks
feat https://github.com/NVIDIA/TensorRT-Edge-LLM/issues/87: add CustomVoice language conditioning support for Qwen3-TTS
#98 opened May 27, 2026 by suharvest Loading…
6 of 8 tasks
6
fix https://github.com/NVIDIA/TensorRT-Edge-LLM/issues/87: hard-error instead of silent return when CuTe DSL GEMM is not compiled
#97 opened May 27, 2026 by suharvest Loading…
6 of 7 tasks
feat: Add multi-stage multi-arch Containerfile
#46 opened Mar 8, 2026 by FreddyFunk Loading…
2
imageUtilKernels.cu: optimize initAttentionMaskKernel
#28 opened Jan 26, 2026 by vitamin-chaos Loading…
@vitamin-chaos
3
ProTip! Follow long discussions with comments:>50.