-
Notifications
You must be signed in to change notification settings - Fork 135
Pull requests: NVIDIA/TensorRT-Edge-LLM
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat: add native continuous batching and chunked prefill for LLM runtime
#215
opened Sep 15, 2026 by
ajmalrasi
Loading…
Fix Qwen3 ONNX export bug related to 0/1 specialization
#213
opened Sep 14, 2026 by
victoroliv2
Loading…
7 tasks
fix https://github.com/NVIDIA/TensorRT-Edge-LLM/issues/211: advance the Philox offset per sampled token
#212
opened Sep 12, 2026 by
filipemartinsubrobotics
Loading…
7 tasks done
fix: say why Int4GroupwiseGemmPluginV2 cannot execute when its kernels are absent
#209
opened Sep 11, 2026 by
filipemartinsubrobotics
Loading…
feat: enable SM103 (B300 / Blackwell Ultra) across the attention SM allowlists
#207
opened Sep 11, 2026 by
filipemartinsubrobotics
Loading…
fix https://github.com/NVIDIA/TensorRT-Edge-LLM/issues/204: pass the CUDA include path to the XQA NVRTC JIT
#205
opened Sep 11, 2026 by
filipemartinsubrobotics
Loading…
fix: Share the target lm_head for DSpark drafts without their own head
#200
opened Sep 9, 2026 by
rain-sicoreai
Loading…
7 tasks done
feat: Add request batching and spec tree-size options to the experimental server, fix FP8-KV and unquantized MTP draft builds
#199
opened Sep 8, 2026 by
rain-sicoreai
Loading…
7 tasks done
feat: add InternVLA-N1-DualVLN vision-language navigation support
#193
opened Aug 24, 2026 by
hungho77
Loading…
6 of 7 tasks
fix(qwen3_5): skip GDN input-projection fusion on mixed projection dt…
#182
opened Aug 17, 2026 by
potoior
Loading…
7 tasks
fix #161: XQA cubin generation ignores resolved output dir under spawn/forkserver
#177
opened Aug 15, 2026 by
Hi5808
Loading…
1 of 2 tasks
fix(qwen3_moe): export W4A16 NVFP4 checkpoints via NVFP4 MoE path
#176
opened Aug 13, 2026 by
potoior
Loading…
3 tasks done
feat(builder): Set workspace RAM limits and enhance log level controls
#126
opened Jul 6, 2026 by
cjac
Loading…
7 tasks done
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…
fix: propagate CuTe DSL runtime link requirements for static libraries
#103
opened Jun 7, 2026 by
francismelon
Loading…
3 of 7 tasks
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
imageUtilKernels.cu: optimize initAttentionMaskKernel
#28
opened Jan 26, 2026 by
vitamin-chaos
Loading…
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.