kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-01-14 06:27:45 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
b959618579
TensorRT-LLMs/tensorrt_llm/_torch
History
nv-guomingz b959618579
refactor [BREAKING CHANGE]:: remove the redundant use_kv_cache field from PytorchConfig (#5031) 
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
2025-06-13 16:34:24 +08:00
..
attention_backend [feat] Optimize KV Cache Reuse for MLA (#4869) 2025-06-13 11:03:05 +08:00
auto_deploy [nvbugs/5331013] fix AutoDeploy for PyTorch 25.05 dependency upgrade (#5106) 2025-06-12 13:07:27 +08:00
compilation [https://nvbugs/5123103][fix] Fix torch compile for DeepSeekV3 (#3952) 2025-05-19 22:12:25 +08:00
custom_ops [TRTLLM-5589] feat: Integrate TRT-LLM Gen FP8 Batched GEMM with Pytorch workflow kernel autotuner (#4872) 2025-06-09 11:02:48 +01:00
distributed Use backend to replace macro to control enablement of MNNVL all reduce (#4635) 2025-06-12 11:22:49 +08:00
models [nvbug/5334370][fix] Fix one model EAGLE3 (#5134) 2025-06-12 10:28:14 -04:00
modules [feat] Optimize KV Cache Reuse for MLA (#4869) 2025-06-13 11:03:05 +08:00
peft feat: support multi lora adapters and TP (#3885) 2025-05-08 23:45:45 +08:00
pyexecutor refactor [BREAKING CHANGE]:: remove the redundant use_kv_cache field from PytorchConfig (#5031) 2025-06-13 16:34:24 +08:00
speculative feat: port MakeDecodingBatchInputOutput to python in TRTLLMSampler (#4828) 2025-06-10 07:28:34 +08:00
__init__.py Update TensorRT-LLM (#2755) 2025-02-11 03:01:00 +00:00
autotuner.py [TRTLLM-5589] feat: Integrate TRT-LLM Gen FP8 Batched GEMM with Pytorch workflow kernel autotuner (#4872) 2025-06-09 11:02:48 +01:00
expert_statistic.py feat: large-scale EP(part 5: Static EP load balancer with offline statistics) (#4695) 2025-06-02 01:25:02 +08:00
llm.py test: [TRTLLM-4334] Create 1.0 criteria scope from API stability references (#3069) 2025-03-26 18:14:35 +08:00
metadata.py feat: no-cache attention in PyTorch workflow (#3085) 2025-04-05 01:54:32 +08:00
model_config.py Use backend to replace macro to control enablement of MNNVL all reduce (#4635) 2025-06-12 11:22:49 +08:00
utils.py feat: Enhance AutoTuner inference path and code readability (#4466) 2025-06-04 10:53:11 +08:00