kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-06 11:11:36 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
f2aee0db03
TensorRT-LLMs/tests/unittest/_torch
History
Ziyi Xiong f2aee0db03
[TRTLLM-9854][feat] Optimize the host overhead of _sample_async (#9935) 
Signed-off-by: ziyixiong-nv <219238287+ziyixiong-nv@users.noreply.github.com>
2025-12-15 13:28:54 +08:00
..
attention [TRTLLM-9416][feat] Skip DS-v3.2 indexer MQA and Top-K for short sequences. (#9524) 2025-12-15 12:42:25 +08:00
auto_deploy [None][feat] AutoDeploy: prepare_metadata revisited (#9764) 2025-12-12 20:14:14 +08:00
compilation [TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804) 2025-05-09 11:04:01 +08:00
debugger Fix: fix nvbug 5356427 (#5464) 2025-06-25 22:24:26 +08:00
executor [TRTLLM-5972][chore] Load balance decode token KV cache with helix parallelism (#9757) 2025-12-12 22:29:05 +08:00
misc [None][fix] Fully resolve the tactic recovery issues in AutoTuner serialized cache (#9835) 2025-12-10 20:41:04 +08:00
modeling [TRTLLM-7967][chore] Add more tests (#9415) 2025-12-08 11:57:32 -08:00
models/checkpoints/hf [TRTLLM-7136][feat] Update load_weights method to include mapping parameter in checkpoint loaders (#9583) 2025-12-05 16:07:20 +01:00
modules [TRTLLM-8961][feat] ConfigurableMoE support DeepGemm (#9858) 2025-12-15 10:47:15 +08:00
multi_gpu [https://nvbugs/5597647][ci] Unwaive fixed tests. (#9812) 2025-12-12 02:29:30 +08:00
multi_gpu_modeling [https://nvbugs/5515753][ci] Add NCCL_DEBUG=INFO flag to collect more info with CI failure. (#8440) 2025-11-20 12:43:13 -05:00
multimodal [TRTLLM-9601][feat] Expose mmKeys for multimodal to integrate with dynamo. (#9604) 2025-12-15 08:42:30 +08:00
ray_orchestrator [TRTLLM-9738][chore] Guard accuracy with nccl allreduce strategy (#9793) 2025-12-13 01:02:11 -08:00
sampler [TRTLLM-9854][feat] Optimize the host overhead of _sample_async (#9935) 2025-12-15 13:28:54 +08:00
speculative [None][feat] Make 2-model spec dec use the 1-model kernels (Hopper) (#8810) 2025-12-09 11:06:31 -05:00
thop [None][feat] Fused kernels (qknormrope + moe routing) and two-model MTP support for glm4moe (#9852) 2025-12-14 10:47:24 +08:00
helpers.py [#8733][feat] Add Llama4 MoE handling to AutoDeploy (#9556) 2025-12-04 08:03:33 +02:00
pattern_watcher.py [TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804) 2025-05-09 11:04:01 +08:00
test_connector.py [None][feat] KV Cache Connector API (#7228) 2025-08-28 23:09:27 -04:00