TensorRT-LLMs

mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00

History

zhhuang-nv 97bc680cd8 feat: support kv cache reuse for MLA (#3571 ) * support kv cache reuse for MLA load compressed_kv and k_pe and do up-projection use 192/128 head size MLA context kernel support Blackwell and Hopper now Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * add CI test Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix: set k_pe head_num to 1 for kernel 2 and kernel 2V2 Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com> * resolve comments Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * use GPTJ style RoPE for MLA Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix rebase error and some docs Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix kv_lens Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * tiny fix Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix torch compile Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix: use normal device memory instead of pinned memory for unit test Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com> * fix L0 tests Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> * fix torch compile after rebase 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> * resolve comments again Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> --------- Signed-off-by: Zhen Huang <145532724+zhhuang-nv@users.noreply.github.com> Signed-off-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com> Signed-off-by: zhhuang-nv <145532724+zhhuang-nv@users.noreply.github.com> Co-authored-by: Mingyang Jiang <13463932+jmydurant@users.noreply.github.com>		2025-05-15 15:22:21 +08:00
..
assert.cpp	Update TensorRT-LLM (#1725 )	2024-06-04 20:26:32 +08:00
attentionOp.cpp	feat: support kv cache reuse for MLA (#3571 )	2025-05-15 15:22:21 +08:00
attentionOp.h	fix: [https://nvbugspro.nvidia.com/bug/5243482 ] If FlashMLA is used, the existence of FMHA based MLA kernels should not be checked. (#3862 )	2025-04-30 14:27:38 +08:00
CMakeLists.txt	Update TensorRT-LLM (#2792 )	2025-02-18 21:27:39 +08:00
cublasMMWrapper.cpp	Update TensorRT-LLM (#2873 )	2025-03-11 21:13:42 +08:00
cublasMMWrapper.h	Update TensorRT-LLM (#2582 )	2024-12-16 21:50:47 -08:00
cublasVersionCheck.h	Initial commit	2023-09-20 00:29:41 -07:00
cudaBf16Fallbacks.cuh	Update TensorRT-LLM (20240116) (#891 )	2024-01-16 20:03:11 +08:00
cudaBufferUtils.cuh	Update TensorRT-LLM (#2783 )	2025-02-13 18:40:22 +08:00
cudaDriverWrapper.cpp	feat: add CGA reduction fmha kernels on Blackwell. (#3763 )	2025-04-29 10:43:54 +08:00
cudaDriverWrapper.h	feat: add CGA reduction fmha kernels on Blackwell. (#3763 )	2025-04-29 10:43:54 +08:00
cudaFp8Utils.cu	Add Llama 4 (#3302 )	2025-04-09 03:35:21 +08:00
cudaProfilerUtils.cpp	Update TensorRT-LLM (#1954 )	2024-07-16 15:30:25 +08:00
cudaTypeUtils.cuh	Update TensorRT-LLM (#2008 )	2024-07-23 23:05:09 +08:00
customAllReduceUtils.h	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
envUtils.cpp	cacheTransceiver buffer manager (#3798 )	2025-04-27 11:48:15 +08:00
envUtils.h	cacheTransceiver buffer manager (#3798 )	2025-04-27 11:48:15 +08:00
jsonSerializeOptional.h	Update TensorRT-LLM (#2436 )	2024-11-12 15:27:49 +08:00
logger.cpp	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
mathUtils.h	Update TensorRT-LLM (#2094 )	2024-08-07 16:44:43 +08:00
memoryUtils.cu	feat: Add group_rms_norm kernel to normalize multiple inputs in a single operator. (#3438 )	2025-05-02 13:25:30 +08:00
memoryUtils.h	Update TensorRT-LLM (#2873 )	2025-03-11 21:13:42 +08:00
nvtxUtils.h	Update TensorRT-LLM (#2755 )	2025-02-11 03:01:00 +00:00
opUtils.cpp	refactor: Introduce MpiTag enumeration and update MPI function signatures (#3893 )	2025-05-04 13:24:29 +02:00
opUtils.h	Update TensorRT-LLM (#2792 )	2025-02-18 21:27:39 +08:00
quantTypeUtils.cuh	Update TensorRT-LLM (#2008 )	2024-07-23 23:05:09 +08:00
reduceKernelUtils.cuh	Update TensorRT-LLM (#2783 )	2025-02-13 18:40:22 +08:00
safetensors.cpp	Update TensorRT-LLM (#2792 )	2025-02-18 21:27:39 +08:00
safetensors.h	Update TensorRT-LLM (#2110 )	2024-08-13 22:34:33 +08:00
stlUtils.h	Update TensorRT-LLM (#1763 )	2024-06-11 16:59:02 +08:00
stringUtils.cpp	chore: Stabilize ABI boundary for internal kernel library (#3117 )	2025-04-11 15:07:50 +08:00
timestampUtils.cpp	Update TensorRT-LLM (#1954 )	2024-07-16 15:30:25 +08:00
timestampUtils.h	Update TensorRT-LLM (#1954 )	2024-07-16 15:30:25 +08:00
tllmException.cpp	chore: Stabilize ABI boundary for internal kernel library (#3117 )	2025-04-11 15:07:50 +08:00
workspace.h	Update TensorRT-LLM (#2184 )	2024-09-03 12:14:23 +02:00