mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-27 22:23:25 +08:00
8452775db8
* optimize kv cache reuse workflow for MLA write kv cache first and only call up-projection GEMM once relax contiguous requirements of k/v for setting paged kv cache return two contiguous tensors when loading MLA KV Cache Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * support fp8 kv cache for MLA kv cache reuse Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * resolve comments Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> --------- Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| mamba | ||
| __init__.py | ||
| attention.py | ||
| decoder_layer.py | ||
| embedding.py | ||
| fused_moe.py | ||
| gated_mlp.py | ||
| linear.py | ||
| logits_processor.py | ||
| mlp.py | ||
| moe_load_balancer.py | ||
| multi_stream_utils.py | ||
| rms_norm.py | ||
| rotary_embedding.py | ||