This website requires JavaScript.
Explore
Help
Sign In
kanshan
/
TensorRT-LLMs
Watch
1
Star
0
Fork
0
You've already forked TensorRT-LLMs
mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced
2026-02-05 10:42:38 +08:00
Code
Issues
Actions
1
Packages
Projects
Releases
Wiki
Activity
f2dd0ee128
TensorRT-LLMs
/
cpp
/
tensorrt_llm
/
executor
History
Chuang Zhu
d6f76d2fae
[TRTLLM-9527][feat] change context params and disagg params (step3) (
#10495
)
...
Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>
2026-01-27 16:34:17 +08:00
..
cache_transmission
[None][chore] Removing pybind11 bindings and references (
#10550
)
2026-01-26 08:19:12 -05:00
cacheTransceiverConfig.cpp
[None][feat] Have ability to cancel disagg request if KV cache resource are exhausted (
#9155
)
2025-11-18 20:59:17 -05:00
CMakeLists.txt
[TRTLLM-9527][feat] Add transferAgent binding (step 1) (
#10113
)
2026-01-06 08:40:38 +08:00
contextPhaseParams.cpp
[TRTLLM-9527][feat] change context params and disagg params (step3) (
#10495
)
2026-01-27 16:34:17 +08:00
debugConfig.cpp
decodingConfig.cpp
disaggServerUtil.cpp
dynamicBatchConfig.cpp
dynamicBatchTuner.cpp
dynamicBatchTuner.h
executor.cpp
executorConfig.cpp
executorImpl.cpp
[TRTLLM-10059][feat] Use global unique id as disagg request id (
#10187
)
2026-01-21 22:52:34 -05:00
executorImpl.h
[TRTLLM-10059][feat] Use global unique id as disagg request id (
#10187
)
2026-01-21 22:52:34 -05:00
executorKVCacheEventManager.cpp
extendedRuntimePerfKnobConfig.cpp
guidedDecodingConfig.cpp
guidedDecodingParams.cpp
intervalSet.h
jsonSerialization.cpp
kvCacheConfig.cpp
fix/improve kvcache allocation in PyTorch runtime (
#5933
)
2025-08-26 12:40:22 +08:00
kvCacheRetentionConfig.cpp
[None][feat] Nixl support for GDS (
#5488
)
2025-09-09 13:00:38 +08:00
logitsPostProcessorConfig.cpp
loraConfig.cpp
model.h
mropeConfig.cpp
multimodalInput.cpp
orchestratorConfig.cpp
orchestratorUtils.h
outputConfig.cpp
parallelConfig.cpp
peftCacheConfig.cpp
promptTuningConfig.cpp
request.cpp
[TRTLLM-10059][feat] Use global unique id as disagg request id (
#10187
)
2026-01-21 22:52:34 -05:00
requestImpl.h
[TRTLLM-10059][feat] Use global unique id as disagg request id (
#10187
)
2026-01-21 22:52:34 -05:00
requestUtils.cpp
requestUtils.h
requestWithId.cpp
requestWithId.h
response.cpp
responseImpl.h
samplingConfig.cpp
[None][feat] Support ignored prompt length for penalties via new sampling config parameter (
#8127
)
2025-10-27 13:12:31 -04:00
schedulerConfig.cpp
serialization.cpp
[TRTLLM-9527][feat] change context params and disagg params (step3) (
#10495
)
2026-01-27 16:34:17 +08:00
serializeUtils.h
[TRTLLM-6106][feat] Add support for KVCache transfer from KVCache reuse path (
#6348
)
2025-09-27 19:29:30 -04:00
speculativeDecodingConfig.cpp
tensor.cpp
[TRTLLM-4629] [feat] Add support of CUDA13 and sm103 devices (
#7568
)
2025-09-16 09:56:18 +08:00
types.cpp