kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-06 19:21:52 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
f07e9977c6
TensorRT-LLMs/tests/unittest/_torch
History
heyuhhh f07e9977c6
[None] [feat] Use triton kernels for RocketKV prediction module (#8682) 
Signed-off-by: yuhangh <58161490+heyuhhh@users.noreply.github.com>
2025-11-13 18:51:09 -08:00
..
attention [None] [feat] Use triton kernels for RocketKV prediction module (#8682) 2025-11-13 18:51:09 -08:00
auto_deploy [None][feat] Add Qwen3-Next to layer-wise benchmarks (#9065) 2025-11-14 10:03:00 +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 [None][chore] Remove is_disaggregated param in executor request queue (#9049) 2025-11-12 13:37:15 -05:00
misc [TRTLLM-8511][feat] Add update_weights and sleep_wakeup support for rl integration (#8302) 2025-11-04 10:19:24 -08:00
modeling [TRTLLM-8521][chore] remove circular dependency between model engine and cuda graph runner (#7572) 2025-11-11 10:13:45 -08:00
models/checkpoints/hf [None][feat] Skip prefetching consolidated safetensors when appropriate (#7013) 2025-08-25 23:56:21 -04:00
modules [https://nvbugs/5565565] [fix] Remove waiver (#8450) 2025-11-04 16:42:31 +08:00
multi_gpu [None][infra] Waive failed cases on main 11/05 (#8936) 2025-11-04 22:54:45 -08:00
multi_gpu_modeling [https://nvbugs/5536131][fix] Fix illegal access issue when scale is not provided in Llama3/4. (#7960) 2025-10-16 22:46:19 +08:00
multimodal [None][fix] InputProcessor config naming convention fix (#8705) 2025-11-03 22:29:21 -08:00
ray_orchestrator [None][chore] Relocate rlhf_utils.py (#8938) 2025-11-10 19:03:23 -08:00
sampler [TRTLLM-9175][test] ensure sampling is async (#9076) 2025-11-12 15:27:52 +01:00
speculative [TRTLLM-8084][feat] Enhance the overlap shceduler for two-model spec decoding (#8706) 2025-11-13 10:20:16 -05:00
thop [None][fix] support topk autotuner input for expert slot per group larger than 32 (#9087) 2025-11-14 08:37:20 +08:00
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