..
attention_backend
[None][fix] Use fp32 for indexer weight_proj GEMM ( #9243 )
2025-11-19 21:52:38 -08:00
auto_deploy
[ #9096 ][feature] Auto Deploy: configurable fused MoE backend ( #9194 )
2025-11-19 21:50:22 -08:00
compilation
[ https://nvbugs/5546510 ][fix] Move torch.cuda.Stream out of torch com… ( #8494 )
2025-11-20 12:43:13 -05:00
configs
[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache ( #8405 )
2025-10-24 13:40:41 -04:00
custom_ops
[TRTLLM-7963][feat] Use CUDAGraph to improve the tuning accuracy for AutoTuner. ( #9089 )
2025-11-20 08:54:29 +08:00
cute_dsl_kernels
[TRTLLM-9286][feat] Integration of CuteDSL NVFP4 grouped GEMM ( #8880 )
2025-11-18 17:40:12 -08:00
debug
Add debug hook to support dump tensor data and add new debug functions easily ( #5182 )
2025-06-24 17:45:28 +08:00
distributed
[None][feat] MNNVLAllreduce Kernel Refactor ( #8018 )
2025-11-05 08:49:47 +08:00
models
[ https://nvbugs/5569713 ][fix] Disable fp8 deep gemm for EXAONE-4.0-32B-FP8 ( #8429 )
2025-11-20 12:43:13 -05:00
modules
[None][fix] Use fp32 for indexer weight_proj GEMM ( #9243 )
2025-11-19 21:52:38 -08:00
peft
[TRTLLM-7346][fix] Improve performance of PyTorchModelEngine._get_lora_params_from_requests ( #7033 )
2025-08-25 10:37:40 +03:00
pyexecutor
[ https://nvbugs/5546510 ][fix] Move torch.cuda.Stream out of torch com… ( #8494 )
2025-11-20 12:43:13 -05:00
shared_tensor
[1/N][TRTLLM-5195][feat] Share PyTorch tensor between processes ( #5396 )
2025-07-10 05:12:53 +09:00
speculative
[None][fix] logits device and shape issues in dynamic draft path ( #9079 )
2025-11-18 19:22:47 -08:00
__init__.py
[TRTLLM-9212][chore] move MoeLoadBalancerConfig to llm_args.py ( #9002 )
2025-11-13 10:47:35 +08:00
autotuner.py
[TRTLLM-7963][feat] Use CUDAGraph to improve the tuning accuracy for AutoTuner. ( #9089 )
2025-11-20 08:54:29 +08:00
cublaslt_utils.py
[ https://nvbugs/5451205 ][feat] Add cuBLASLt NVFP4 GEMM backend support ( #7943 )
2025-10-23 15:55:10 +08:00
cute_dsl_utils.py
[None][chore] polish error message in cute_dsl_utils.py ( #7852 )
2025-09-19 12:05:11 +08:00
device_mesh.py
[TRTLLM-8682][chore] Remove auto_parallel module ( #8329 )
2025-10-22 20:53:08 -04:00
expert_statistic.py
[TRTLLM-8831][feat] Enable early exit with overlap scheduler ( #8587 )
2025-11-17 18:07:13 +01:00
flashinfer_utils.py
[None][ci] move unittests to sub-directories ( #6635 )
2025-08-20 05:42:22 -04:00
hostfunc.py
[TRTLLM-7028][feat] Enable guided decoding with speculative decoding (part 2: one-model engine) ( #6948 )
2025-09-03 15:16:11 -07:00
llm.py
[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default ( #5312 )
2025-06-20 03:01:10 +08:00
memory_buffer_utils.py
[TRTLLM-8690][feat] add more tensors to share buffers ( #8691 )
2025-11-03 21:08:01 -08:00
metadata.py
[None][feat] Use Separate QKV Input Layout for Context MLA ( #6538 )
2025-08-19 22:04:48 +08:00
model_config.py
[None][fix] Update the attention layers counting for Qwen3-next. ( #9072 )
2025-11-16 11:52:56 -08:00
utils.py
[ https://nvbugs/5667687 ][fix] Set correct lm_head_tp_size_upper_bound ( #9300 )
2025-11-20 00:41:00 -08:00
virtual_memory.py
[TRTLLM-8511][feat] Add update_weights and sleep_wakeup support for rl integration ( #8302 )
2025-11-04 10:19:24 -08:00
3454eacd74