kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-27 14:13:34 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
34e63d07e6
TensorRT-LLMs/tests/unittest/_torch
History
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
..
auto_deploy test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
compilation Update (#2978) 2025-03-23 16:39:35 +08:00
modeling test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
multi_gpu perf: Add optimizations for deepseek in min latency mode (#3093) 2025-04-02 09:05:24 +08:00
multi_gpu_modeling fix：fix illeagel memory access when mtp >= 2 (#3006) 2025-04-01 13:36:45 +08:00
speculative Add initial EAGLE-3 implementation (#3035) 2025-03-29 22:31:24 +08:00
thop perf: Add optimizations for deepseek in min latency mode (#3093) 2025-04-02 09:05:24 +08:00
helpers.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
pattern_watcher.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
test_attention.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_autotuner.py Update (#2978) 2025-03-23 16:39:35 +08:00
test_flashinfer_attention.py Update (#2978) 2025-03-23 16:39:35 +08:00
test_flashinfer_star_attn.py Update (#2978) 2025-03-23 16:39:35 +08:00
test_fp4_bmm_quantize.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_fp4_gemm_quantize.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_fp4_linear.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_fp8_block_scale_gemm.py fix: Update FP8 sf layout for Blackwell and relax blockwise GEMM assertions (#3144) 2025-04-01 13:08:29 -07:00
test_fp8_linear.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_fp8_quantize.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_fused_moe.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_moe_routing.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
test_moe.py test: reorganize tests folder hierarchy (#2996) 2025-03-27 12:07:53 +08:00
test_overlap_scheduler_input.json Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
test_overlap_scheduler.py Update TensorRT-LLM (#2936) 2025-03-18 21:25:19 +08:00
test_pytorch_model_engine.py Update (#2978) 2025-03-23 16:39:35 +08:00
test_vanilla_attention.py Update (#2978) 2025-03-23 16:39:35 +08:00