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
..
auto_deploy	Waive L0 test (#4609)	2025-05-23 15:54:11 +08:00
compilation	[TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804)	2025-05-09 11:04:01 +08:00
modeling	[TRTLLM-5085][fix] Nemotron H correctness test (#4444)	2025-05-20 17:55:25 +08:00
modules	feat: large-scale EP(part 2: MoE Load Balancer - core utilities) (#4384)	2025-05-20 17:53:48 +08:00
multi_gpu	Adding two-shot allreduce kernel and mnnvl multicasting buffer (#4216)	2025-05-22 03:42:36 +08:00
multi_gpu_modeling	perf: Eliminate the need for attention DP padding when possible (#3439)	2025-05-17 13:30:55 +08:00
speculative	[TRTLLM-5000][feat] Pytorch implementation of ngram drafter (#3936)	2025-05-21 10:40:00 +08:00
thop	Qwen3 supports TRTLLM FP4 MoE backend (#4530)	2025-05-23 18:31:08 +08:00
helpers.py	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
pattern_watcher.py	[TRTLLM-3105][feat] Add Piecewise CUDA Graph Support (#3804)	2025-05-09 11:04:01 +08:00
test_attention_mla.py	[Feat] add chunked-attention kernels on Hopper (for llama4) (#4291)	2025-05-19 09:57:10 -07:00
test_attention_no_cache.py	refactor(test): remove random context sequence lengths and set seed for reproducibility in attention tests (#3919)	2025-04-29 10:08:04 +08:00
test_attention.py	reduce num layers in attention test (#3509)	2025-04-14 12:43:59 +08:00
test_autotuner.py	chore: Mass Integration 0.19 (#4255)	2025-05-16 10:53:25 +02:00
test_flashinfer_attention.py	Add thread leak check and fix thread/memory leak issues. (#3270)	2025-04-08 19:03:18 +08:00
test_flashinfer_star_attn.py	Add thread leak check and fix thread/memory leak issues. (#3270)	2025-04-08 19:03:18 +08:00
test_fp8_per_tensor_scale_tllmg_gemm.py	Cherry-pick trtllm-gen from feat/llama4 to main (#4086)	2025-05-08 14:13:01 -07:00
test_group_rmn_norm.py	feat: Add heuristic for GroupRMSNorm kernel selection. (#4047)	2025-05-13 08:52:53 +08:00
test_mnnvl_memory.py	feat: Add MNNVL MoE A2A support (#3504)	2025-04-25 17:29:08 +08:00
test_overlap_scheduler_input.json	refactor: Unify request order in TRT and PyTorch workflow (#4096)	2025-05-20 18:49:27 +02:00
test_overlap_scheduler.py	API Breaking Change + Readability: "decoder"->"sampler" (#4121)	2025-05-16 23:52:25 +08:00
test_pytorch_model_engine.py	chore: move all distributed related codes into _torch.distributed directory (#3511)	2025-04-15 08:39:17 +08:00
test_resource_manager.py	feat: support multi lora adapters and TP (#3885)	2025-05-08 23:45:45 +08:00
test_return_logits.py	feat: adopt new logprob definition in PyTorch flow (#4057)	2025-05-08 20:16:40 +08:00
test_trtllm_sampler.py	API Breaking Change + Readability: "decoder"->"sampler" (#4121)	2025-05-16 23:52:25 +08:00
test_vanilla_attention.py	Add thread leak check and fix thread/memory leak issues. (#3270)	2025-04-08 19:03:18 +08:00