TensorRT-LLMs/tensorrt_llm/layers
Haohang Huang 980929e1a9
[https://nvbugs/5410687][fix] Hopper w4a8 groupwise MoE interleave (#6708)
Signed-off-by: Haohang Huang <31998628+symphonylyh@users.noreply.github.com>
2025-08-07 15:30:16 -07:00
..
__init__.py
activation.py
attention.py feat: TRTLLM-6450 update long rope for phi3.5/phi4-mini/phi4-mm (#6353) 2025-07-30 09:20:16 -07:00
cast.py
conv.py
embedding.py fix: #3137 speculative decoding and multimodal input support (#3276) 2025-04-09 23:40:19 +08:00
language_adapter.py
linear.py
lora.py
mlp.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
moe.py [https://nvbugs/5410687][fix] Hopper w4a8 groupwise MoE interleave (#6708) 2025-08-07 15:30:16 -07:00
normalization.py
pooling.py
recurrent.py
ssm.py