..
attention_backend
[None][feat] Add support for KVCache reuse for DSv32 ( #9383 )
2025-12-02 11:14:30 +08:00
auto_deploy
[None][feat] AutoDeploy: Perf optimization for Attention and rmsnorm ( #9719 )
2025-12-05 12:59:04 -08:00
compilation
[TRTLLM-9660][feat] Convert cuteDSL GEMM to opt-in feature ( #9682 )
2025-12-06 02:24:51 -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
[TRTLLM-9660][feat] Convert cuteDSL GEMM to opt-in feature ( #9682 )
2025-12-06 02:24:51 -08:00
cute_dsl_kernels
[TRTLLM-9372][feat] Enable CuteDSL MoE with Large EP ( #9592 )
2025-12-05 22:08:52 -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
[TRTLLM-7073][feat] Support torch compile for PP for Llama and DeepSeekV3 ( #7838 )
2025-12-04 13:32:11 +08:00
models
[None][fix] Update branch with the correct extra_attrs fix ( #9857 )
2025-12-10 10:42:35 +08:00
modules
[None][fix] Update branch with the correct extra_attrs fix ( #9857 )
2025-12-10 10:42:35 +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/5677746 ][fix] Use first PP rank's schedule result in other PP ranks to fix PP hang ( #9659 )
2025-12-09 16:46:36 +08:00
shared_tensor
[1/N][TRTLLM-5195][feat] Share PyTorch tensor between processes ( #5396 )
2025-07-10 05:12:53 +09:00
speculative
[None][fix] Fix TLLM_SPEC_DECODE_FORCE_NUM_ACCEPTED_TOKENS for MTP/EAGLE ( #9608 )
2025-12-04 08:23:57 -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-9372][feat] Enable CuteDSL MoE with Large EP ( #9592 )
2025-12-05 22:08:52 -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
[TRTC-1943][feat] Env vars override support in LLM API ( #9104 )
2025-12-01 10:04:49 -08:00
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
[TRTLLM-9660][feat] Convert cuteDSL GEMM to opt-in feature ( #9682 )
2025-12-06 02:24:51 -08:00
utils.py
[FMDL-1328][feat] Add support for nano-v3 and super-v3 with pytorch backend ( #9261 )
2025-12-02 13:40:20 +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
b05481107c