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
18fbda5cdb
TensorRT-LLMs/tests/unittest/_torch
History
Chenghao Zhang 18fbda5cdb
[None][feat] AutoDeploy: Add A_log fusion for Mamba layers (#9422) 
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
2025-11-26 14:39:20 -08:00
..
attention [None][feat] Support MLA chunked prefill for DeepSeek V3.2 model (#9376) 2025-11-26 16:38:25 +08:00
auto_deploy [None][feat] AutoDeploy: Add A_log fusion for Mamba layers (#9422) 2025-11-26 14:39:20 -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-8650][fix] beam search request validation (#8433) (#9228) 2025-11-21 04:08:45 -08:00
misc [TRTLLM-7963][feat] Use CUDAGraph to improve the tuning accuracy for AutoTuner. (#9089) 2025-11-20 08:54:29 +08:00
modeling [TRTLLM-9264][fix] Add accuracy/unit tests/doc for phi4mm (#9246) 2025-11-26 11:12:35 +08:00
models/checkpoints/hf [None][feat] Skip prefetching consolidated safetensors when appropriate (#7013) 2025-08-25 23:56:21 -04:00
modules [TRTLLM-9370][feat] Integration of CuteDSL NVFP4 grouped GEMM (Part 2: SwiGLU Fusion and Finalize Fusion) (#9288) 2025-11-21 14:03:38 -08:00
multi_gpu [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
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 [None][fix] InputProcessor config naming convention fix (#8705) 2025-11-03 22:29:21 -08:00
ray_orchestrator [TRTLLM-9293][feat] Enable partial weight loading to support streaming update weights (#9224) 2025-11-26 10:59:06 +08:00
sampler [TRTLLM-9490][feat] use FlashInfer's top_k_sampling_from_probs (#9457) 2025-11-25 18:53:53 +01:00
speculative [TRTLLM-8160][feat] Add draft token tree runtime on CDL (#8586) 2025-11-25 09:40:55 -05:00
thop [TRTLLM-8160][feat] Add draft token tree runtime on CDL (#8586) 2025-11-25 09:40:55 -05:00
helpers.py [TRTLLM-8521][chore] remove circular dependency between model engine and cuda graph runner (#7572) 2025-11-11 10:13:45 -08:00
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