| .. |
|
attention_backend
|
[None][feat] Use Separate QKV Input Layout for Context MLA (#6538)
|
2025-08-19 22:04:48 +08:00 |
|
auto_deploy
|
[None][opt] Add batch wait timeout in fetching requests (#6923)
|
2025-08-19 03:50:08 -04:00 |
|
compilation
|
[None][refactor] Refactor Torch Compile Backend, MoeLoadBalancer and warmup Logic (#6615)
|
2025-08-19 09:58:44 +08:00 |
|
custom_ops
|
[None][refactor] Refactor Torch Compile Backend, MoeLoadBalancer and warmup Logic (#6615)
|
2025-08-19 09:58:44 +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/5445466][fix] fix deepseek r1 hang by not enabling mnnvl by default (#6860)
|
2025-08-14 22:36:56 +08:00 |
|
models
|
[None][feat] Use Separate QKV Input Layout for Context MLA (#6538)
|
2025-08-19 22:04:48 +08:00 |
|
modules
|
[None][feat] Use Separate QKV Input Layout for Context MLA (#6538)
|
2025-08-19 22:04:48 +08:00 |
|
peft
|
feat: support multi lora adapters and TP (#3885)
|
2025-05-08 23:45:45 +08:00 |
|
pyexecutor
|
[None][feat] Use Separate QKV Input Layout for Context MLA (#6538)
|
2025-08-19 22:04:48 +08:00 |
|
shared_tensor
|
[1/N][TRTLLM-5195][feat] Share PyTorch tensor between processes (#5396)
|
2025-07-10 05:12:53 +09:00 |
|
speculative
|
[https://nvbugs/5455651][fix] Make ngram use XQA attention on Blackwell (#6873)
|
2025-08-14 18:36:19 -04:00 |
|
__init__.py
|
[nvbugs/5401156][fix] Avoid import all models when import trtllm._common (#6266)
|
2025-07-27 23:29:21 -04:00 |
|
autotuner.py
|
[TRTLLM-4501][feat] AutoTuner tuning config refactor and valid tactic generalization. (#6545)
|
2025-08-13 16:25:22 +08:00 |
|
expert_statistic.py
|
Add MTP support for Online EPLB (#5213)
|
2025-06-25 07:58:13 +08:00 |
|
llm.py
|
[TRTLLM-5208][BREAKING CHANGE] chore: make pytorch LLM the default (#5312)
|
2025-06-20 03:01:10 +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] Correct reporting of torch_dtype for ModelConfig class. (#6800)
|
2025-08-14 22:46:20 -04:00 |
|
utils.py
|
[None][refactor] Refactor Torch Compile Backend, MoeLoadBalancer and warmup Logic (#6615)
|
2025-08-19 09:58:44 +08:00 |
|
virtual_memory.py
|
[TRTLLM-4406][feat] LLM sleep & wakeup Part 1: virtual device memory (#5034)
|
2025-08-04 13:51:01 +08:00 |
