TensorRT-LLMs/cpp/tensorrt_llm
DylanChen-NV 206f82115d
[bug/5247505] fix: CP accuracy on Blackwell (#4188)
* fix xqa params for cp

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

* add test

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

* add test

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

* try adding B200 multi gpu test

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

* add accuracy tests for cp

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>

---------

Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
2025-05-14 17:40:50 +08:00
..
batch_manager Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979) 2025-05-12 22:32:29 +02:00
common [bug/5247505] fix: CP accuracy on Blackwell (#4188) 2025-05-14 17:40:50 +08:00
cutlass_extensions/include/cutlass_extensions [TRTLLM-3330][feat] Support DeepSeek-R1 W4A8 on Hopper (#4123) 2025-05-14 15:48:07 +08:00
executor Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979) 2025-05-12 22:32:29 +02:00
executor_worker Update TensorRT-LLM (#2792) 2025-02-18 21:27:39 +08:00
kernels feat: Low Precision Allreduce for PCIe based GPU (#3851) 2025-05-14 16:45:43 +08:00
layers Feat: Variable-Beam-Width-Search (VBWS) part4 (#3979) 2025-05-12 22:32:29 +02:00
plugins Support RingAttention in the BertAttention plugin and the DiT model (#3661) 2025-05-09 08:06:54 +08:00
pybind feat: Low Precision Allreduce for PCIe based GPU (#3851) 2025-05-14 16:45:43 +08:00
runtime [TRTLLM-3330][feat] Support DeepSeek-R1 W4A8 on Hopper (#4123) 2025-05-14 15:48:07 +08:00
testing refactor: Move ModelSpec to core library (#3980) 2025-05-04 01:39:09 +08:00
thop feat: Low Precision Allreduce for PCIe based GPU (#3851) 2025-05-14 16:45:43 +08:00
CMakeLists.txt Cherry-pick trtllm-gen from feat/llama4 to main (#4086) 2025-05-08 14:13:01 -07:00