| .. |
|
batch_manager
|
feat:enable kvcache to be reused during request generation (#4028)
|
2025-07-10 22:18:01 +09:00 |
|
common
|
[TRTLLM-5366][feat]Add support for sm121 (#5524)
|
2025-07-08 14:27:00 -07:00 |
|
cutlass_extensions/include/cutlass_extensions
|
Fix GEMM+AR fusion on blackwell (#5563)
|
2025-07-09 08:48:47 +08:00 |
|
deep_ep
|
Fix a quote error introduced in #5534 (#5816)
|
2025-07-08 18:48:32 +08:00 |
|
executor
|
feat: KV events for sliding window attention (#5580)
|
2025-07-05 06:05:20 +08:00 |
|
executor_worker
|
Update TensorRT-LLM (#2792)
|
2025-02-18 21:27:39 +08:00 |
|
kernels
|
[fix] fix tileN cannot % 16==0 & support sm89 deepgemm bmm (#5531)
|
2025-07-10 15:16:18 +08:00 |
|
layers
|
Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979)
|
2025-05-12 22:32:29 +02:00 |
|
nanobind
|
feat: binding type build argument (pybind, nanobind) (#5802)
|
2025-07-11 00:48:50 +09:00 |
|
plugins
|
[NVBUG-5304516/5319741]Qwen2.5VL FP8 support (#5029)
|
2025-07-09 23:16:42 +08:00 |
|
pybind
|
feat: binding type build argument (pybind, nanobind) (#5802)
|
2025-07-11 00:48:50 +09:00 |
|
runtime
|
Fix GEMM+AR fusion on blackwell (#5563)
|
2025-07-09 08:48:47 +08:00 |
|
testing
|
fix: Improve chunking test and skip empty kernel calls (#5710)
|
2025-07-04 09:08:15 +02:00 |
|
thop
|
[fix] Fix MoE workspace info by storing Torch tensor itself instead of data_ptr (#5900)
|
2025-07-10 20:07:32 +09:00 |
|
CMakeLists.txt
|
feat: binding type build argument (pybind, nanobind) (#5802)
|
2025-07-11 00:48:50 +09:00 |
