mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
129bf19980
* add qwen3 dense model pytorch backend support, initial commit solve the results error issue add qwen3 moe model pytorch backend support reformat the code * perf - use flash_infer rmsnorm for qwen3 * feat - support qwen3 moe rmsnorm * Put the computation of Q and K norm (in attn) into a single CUDA stream, and get a 5% - 8% throughput improvement on Qwen3 4B and Qwen3 - moe 30B - A3B. * Put the computation of Q and K norm (in attn) into a single CUDA stream, and get a 5% - 8% throughput improvement on Qwen3 4B and Qwen3 - moe 30B - A3B. -- Forgot to update all modifications. * fix bugs of running qwen3 public models and fp8 models Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com> * fix bugs due to rebase Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com> * fix bugs captured by pre-commi Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com> * fix bug of attention Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com> --------- Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com> Co-authored-by: Keddy Jin <jin.gq@aliyun.com> Co-authored-by: Jiying Dong <87510204+dongjiyingdjy@users.noreply.github.com> Co-authored-by: shao <shao@nvidia.com> |
||
|---|---|---|
| .. | ||
| mamba | ||
| __init__.py | ||
| attention.py | ||
| decoder_layer.py | ||
| embedding.py | ||
| fused_moe.py | ||
| gated_mlp.py | ||
| linear.py | ||
| logits_procesor.py | ||
| mlp.py | ||
| multi_stream_utils.py | ||
| rms_norm.py | ||
| rotary_embedding.py | ||