..
attention_backend
[None][chore] update flashinfer to 0.6.0 ( #10522 )
2026-01-16 16:22:06 -05:00
auto_deploy
[TRTLLM-10318][feat] Fixing Nemotron sharding: support for sharding buffers ( #10319 )
2026-01-17 04:02:06 -05:00
compilation
[TRTLLM-8821][feat] Apply AutoTuner to AllReduce Op for strategy tuning. ( #8531 )
2026-01-05 15:44:37 +08:00
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
[None][fix] Fix Piecewise Cuda Graph for GPTOSS ( #10631 )
2026-01-16 15:47:34 +08:00
cute_dsl_kernels
[None] [feat] Add test script and raster M for gather fc1 kernel ( #10429 )
2026-01-07 09:31:49 +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
[ https://nvbugs/5782112 ][fix] Fix hanging issue for MNNVL Allreduce under PP ( #10633 )
2026-01-16 13:03:36 +08:00
models
[None][feat] Auto download speculative models from HF for pytorch backend, add speculative_model field alias ( #10099 )
2026-01-14 21:06:07 -08:00
modules
[None][fix] add quantization check for DeepEP LL low precision combine in new moe comm api ( #10072 )
2026-01-14 22:15:29 -05:00
peft
[TRTLLM-7346][fix] Improve performance of PyTorchModelEngine._get_lora_params_from_requests ( #7033 )
2025-08-25 10:37:40 +03:00
pyexecutor
[TRTLLM-9735][feat] Add processed logprobs functionality to TorchSampler ( #9675 )
2026-01-16 10:52:41 -08:00
shared_tensor
[1/N][TRTLLM-5195][feat] Share PyTorch tensor between processes ( #5396 )
2025-07-10 05:12:53 +09:00
speculative
[TRTLLM-9735][feat] Add processed logprobs functionality to TorchSampler ( #9675 )
2026-01-16 10:52:41 -08:00
__init__.py
[TRTLLM-9212][chore] move MoeLoadBalancerConfig to llm_args.py ( #9002 )
2025-11-13 10:47:35 +08:00
async_llm.py
[TRTLLM-9736][feat] AsyncLLM and verl integ ( #9353 )
2025-12-11 09:33:25 -08:00
autotuner.py
[None][refactor] Unify the usage of MPIDist and TorchDist. ( #10380 )
2026-01-14 14:05:47 +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-9465][fix] Swap TP-CP grouping order ( #10350 )
2026-01-05 20:08:03 +08:00
expert_statistic.py
[TRTLLM-8831][feat] Enable early exit with overlap scheduler ( #8587 )
2025-11-17 18:07:13 +01:00
flashinfer_utils.py
[TRTLLM-9578][feat] make PDL enabled by default ( #9695 )
2025-12-25 07:15:24 -05:00
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
[ https://nvbugs/5629833 ][fix] Don't fill tensors with 0 ( #9296 )
2025-11-21 20:50:05 +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
[ https://nvbugs/5762336 ][fix] support to parse the keyword modules_to_not_convert of the HF model config" ( #10527 )
2026-01-12 20:21:01 -05:00
utils.py
[TRTLLM-10309] [feat] Optimize qk rope/nope concat for DSA ( #10571 )
2026-01-09 09:50:57 -05:00
virtual_memory.py
[TRTLLM-9736][feat] AsyncLLM and verl integ ( #9353 )
2025-12-11 09:33:25 -08:00
7bf4dd9f63