TensorRT-LLMs/tests/unittest/_torch/multi_gpu
Zongfei Jing c7548ad72c
perf: Add optimizations for deepseek in min latency mode (#3093)
* Add optimizations for deepseek min latency

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Fix compile error

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Update internal cutlass kernel libs

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Format code

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

* Resolve conflicts

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>

---------

Signed-off-by: Zongfei Jing <20381269+zongfeijing@users.noreply.github.com>
2025-04-02 09:05:24 +08:00
..
test_ar_residual_norm.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_deepseek_allreduce.py perf: Add optimizations for deepseek in min latency mode (#3093) 2025-04-02 09:05:24 +08:00
test_embedding.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
test_linear.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
test_star_attention_input.jsonl Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
test_star_attention.py move BuildConfig functional args to llmargs (#3036) 2025-03-29 02:20:18 +08:00
test_user_buffers.py None - Add one-shot version for UB AR NORM FP16/BF16 (#2995) 2025-03-31 11:16:03 +08:00