kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
bbea2647b1
TensorRT-LLMs/cpp/tensorrt_llm/thop
History
Anthony Chang bbea2647b1
Qwen3 supports TRTLLM FP4 MoE backend (#4530) 
* MoE TRTLLM backend for Qwen3

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* add extra moe_backend to test

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* address comments

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* conditionally compile kernels on newer archs

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* missing positional arg

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* Update the routing kernels

Signed-off-by: Christina Zhang <christinaz@nvidia.com>

* Revise usage of TLLM_LOG_ERROR

Signed-off-by: Christina Zhang <christinaz@nvidia.com>

* Add unit test for Qwen3 moe (trtllm_gen backend)

Signed-off-by: Christina Zhang <christinaz@nvidia.com>

* improve weight processing speed of moe_backend=TRTLLM; roughly 2x

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* tidy and minor fix

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

* temporarily disable accuracy test that has known issue

Signed-off-by: Anthony Chang <anchengc@nvidia.com>

---------

Signed-off-by: Anthony Chang <anchengc@nvidia.com>
Signed-off-by: Christina Zhang <christinaz@nvidia.com>
Co-authored-by: Christina Zhang <christinaz@nvidia.com>
2025-05-23 18:31:08 +08:00
..
allgatherOp.cpp perf: Eliminate the need for attention DP padding when possible (#3439) 2025-05-17 13:30:55 +08:00
allreduceOp.cpp Adding two-shot allreduce kernel and mnnvl multicasting buffer (#4216) 2025-05-22 03:42:36 +08:00
attentionOp.cpp [feat] Integrate Hopper chunked attention kernels (#4330) 2025-05-22 17:10:57 -04:00
CMakeLists.txt perf: Add fused q_norm/k_norm/RoPE for Qwen3. (#4482) 2025-05-23 15:31:04 +08:00
convertSpecDecodingMaskToPackedMaskOp.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
cublasScaledMM.cpp [fix] Remove stale cublas heuristics (#4326) 2025-05-14 17:35:51 -07:00
cutlassScaledMM.cpp feat: support add internal cutlass kernels as subproject (#3658) 2025-05-06 11:35:07 +08:00
dynamicDecodeOp.cpp Feat: Variable-Beam-Width-Search (VBWS) part3 (#3338) 2025-04-08 23:51:27 +08:00
dynamicDecodeOp.h Update TensorRT-LLM (#2783) 2025-02-13 18:40:22 +08:00
fmhaPackMaskOp.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
fp4BatchedQuantize.cpp update FP4 quantize layout (#3045) 2025-04-03 13:13:54 -04:00
fp4BlockScaleMoe.cpp Qwen3 supports TRTLLM FP4 MoE backend (#4530) 2025-05-23 18:31:08 +08:00
fp4Gemm.cpp feat: support add internal cutlass kernels as subproject (#3658) 2025-05-06 11:35:07 +08:00
fp4GemmTrtllmGen.cpp Cherry-pick trtllm-gen from feat/llama4 to main (#4086) 2025-05-08 14:13:01 -07:00
fp4Op.cpp feat: [Deepseek] Add trtllm-gen MOE FP4 MOE backend (#3387) 2025-04-21 10:01:33 +08:00
fp4Quantize.cpp feat: Fallback to NCCL for various patterns when input size is large. (#4080) 2025-05-08 11:13:13 -07:00
fp4Quantize.h feat: Fallback to NCCL for various patterns when input size is large. (#4080) 2025-05-08 11:13:13 -07:00
fp8BatchedGemmTrtllmGen.cpp feat: TRT-LLM Gen integration for BMM and MoE refactoring (#4280) 2025-05-16 13:31:53 +02:00
fp8BlockScaleMoe.cpp Qwen3 supports TRTLLM FP4 MoE backend (#4530) 2025-05-23 18:31:08 +08:00
fp8BlockScalingGemm.cpp [feat] support fp8 blockscale gemm on sm89 (#4481) 2025-05-23 10:39:10 +08:00
fp8Op.cpp feat: Fallback to NCCL for various patterns when input size is large. (#4080) 2025-05-08 11:13:13 -07:00
fp8Op.h feat: Fallback to NCCL for various patterns when input size is large. (#4080) 2025-05-08 11:13:13 -07:00
fp8PerTensorScaleMoe.cpp Qwen3 supports TRTLLM FP4 MoE backend (#4530) 2025-05-23 18:31:08 +08:00
fp8PerTensorScalingTrtllmGenGemm.cpp Cherry-pick trtllm-gen from feat/llama4 to main (#4086) 2025-05-08 14:13:01 -07:00
fp8Quantize.cpp [feat] open source fp8_blockscale_gemm (#3071) 2025-04-02 12:12:52 +08:00
fusedQKNormRopeOp.cpp perf: Add fused q_norm/k_norm/RoPE for Qwen3. (#4482) 2025-05-23 15:31:04 +08:00
fusedTopkSoftmax.cpp feat: support add internal cutlass kernels as subproject (#3658) 2025-05-06 11:35:07 +08:00
gatherTreeOp.cpp [TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow (#4092) 2025-05-14 23:10:04 +02:00
groupRmsNormOp.cpp feat: Add heuristic for GroupRMSNorm kernel selection. (#4047) 2025-05-13 08:52:53 +08:00
logitsBitmaskOp.cpp Update (#2978) 2025-03-23 16:39:35 +08:00
loraOp.cpp added loraOp into lora layer + test for mlp and comparison to lora plugin (#3455) 2025-04-17 12:48:27 +08:00
mambaConv1dOp.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
mlaPreprocessOp.cpp feat: support kv cache reuse for MLA (#3571) 2025-05-15 15:22:21 +08:00
moeCommOp.cpp feat: Add MNNVL MoE A2A support (#3504) 2025-04-25 17:29:08 +08:00
moeLoadBalanceOp.cpp feat: large-scale EP(part 2: MoE Load Balancer - core utilities) (#4384) 2025-05-20 17:53:48 +08:00
moeOp.cpp perf: Fuse gemm setup function for SM90/SM100 MOE plugin path (#4146) 2025-05-21 10:00:36 +08:00
mtpOp.cpp [https://nvbugs/5123103][fix] Fix torch compile for DeepSeekV3 (#3952) 2025-05-19 22:12:25 +08:00
ncclCommunicatorOp.cpp feat: [nvbugs/5261055][nvbugs/5170160] non-invasive pipeline parallelism (#4034) 2025-05-16 04:16:53 +08:00
ncclCommunicatorOp.h feat: [nvbugs/5261055][nvbugs/5170160] non-invasive pipeline parallelism (#4034) 2025-05-16 04:16:53 +08:00
noAuxTcOp.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
parallelDecodeKVCacheUpdateOp.cpp Update TensorRT-LLM (#2582) 2024-12-16 21:50:47 -08:00
redrafterCurandOp.cpp [TRTLLM-5171] chore: Remove GptSession/V1 from TRT workflow (#4092) 2025-05-14 23:10:04 +02:00
reducescatterOp.cpp perf: Eliminate the need for attention DP padding when possible (#3439) 2025-05-17 13:30:55 +08:00
relativeAttentionBiasOp.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
selectiveScanOp.cpp Update TensorRT-LLM (#2873) 2025-03-11 21:13:42 +08:00
thUtils.cpp Update TensorRT-LLM (#2849) 2025-03-04 18:44:00 +08:00
thUtils.h feat: Low Precision Allreduce for PCIe based GPU (#4344) 2025-05-20 06:53:46 +08:00
userbuffersFinalizeOp.cpp feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
userbuffersTensor.cpp feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
userbuffersTensor.h feat: Introduce UB allocator for pytorch flow (#3257) 2025-04-08 18:39:49 +08:00
weightOnlyQuantOp.cpp chore: remove usernames from comments (#3291) 2025-04-05 13:44:28 +08:00