Chuang Zhu ee471df07c [None][chore] optimize kv cache transfer for context TEP and gen DEP (#6657) ... Signed-off-by: Chuang Zhu <111838961+chuangz0@users.noreply.github.com>		2025-08-07 11:36:05 +08:00
..
utils
allocateKvCache.cpp
assignReqSeqSlots.cpp
cacheFormatter.cpp	[None][chore] optimize kv cache transfer for context TEP and gen DEP (#6657)	2025-08-07 11:36:05 +08:00
cacheFormatter.h	[TRTLLM-6549] chore: record delay introduced by disaggregated serving in kv cache measure (#6135)	2025-07-30 10:39:40 +08:00
cacheTransBuffer.cpp
cacheTransBuffer.h
cacheTransceiver.cpp	[None][chore] ucx establish connection with zmq (#6090)	2025-08-05 02:50:45 -04:00
capacityScheduler.cpp
CMakeLists.txt	feat: Support structural tag in C++ runtime and upgrade xgrammar to 0.1.21 (#6408)	2025-07-31 09:53:52 +08:00
contextProgress.cpp
createNewDecoderRequests.cpp	[None][refactor] Simplify finish reasons handling in DecoderState (#6524)	2025-08-02 07:17:43 +02:00
dataTransceiver.cpp
dataTransceiver.h	[TRTLLM-6549] chore: record delay introduced by disaggregated serving in kv cache measure (#6135)	2025-07-30 10:39:40 +08:00
dataTransceiverImpl.cpp	[TRTLLM-6549] chore: record delay introduced by disaggregated serving in kv cache measure (#6135)	2025-07-30 10:39:40 +08:00
dataTransceiverImpl.h
decoderBuffers.cpp
encoderBuffers.cpp
encoderBuffers.h
evictionPolicy.cpp
guidedDecoder.cpp	feat: Support structural tag in C++ runtime and upgrade xgrammar to 0.1.21 (#6408)	2025-07-31 09:53:52 +08:00
handleContextLogits.cpp
handleGenerationLogits.cpp
kvCacheEventManager.cpp
kvCacheManager.cpp	fix: remove duplicate layer multiplication in KV cache size calculation (#6481)	2025-07-31 22:34:34 -04:00
kvCacheTransferManager.cpp
llmRequest.cpp	[TRTLLM-5508][feat] check input tokens + improve error handling (#5170)	2025-08-05 18:27:43 +01:00
logitsPostProcessor.cpp
loraBuffers.cpp
loraBuffers.h
makeDecodingBatchInputOutput.cpp
medusaBuffers.cpp
microBatchScheduler.cpp
mlaCacheFormatter.cpp	[None][chore] optimize kv cache transfer for context TEP and gen DEP (#6657)	2025-08-07 11:36:05 +08:00
mlaCacheFormatter.h	[TRTLLM-6549] chore: record delay introduced by disaggregated serving in kv cache measure (#6135)	2025-07-30 10:39:40 +08:00
pauseRequests.cpp
peftCacheManager.cpp
promptTuningBuffers.cpp
rnnStateBuffers.cpp
rnnStateBuffers.h
rnnStateManager.cpp
runtimeBuffers.cpp
scheduledBlocksManager.h
sequenceSlotManager.cpp
transformerBuffers.cpp
trtEncoderModel.cpp
trtEncoderModel.h
trtGptModel.h
trtGptModelFactory.h
trtGptModelInflightBatching.cpp	[nvbug/5374773] chore: Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache (#5974)	2025-07-25 18:10:40 -04:00
trtGptModelInflightBatching.h	[nvbug/5374773] chore: Add a runtime flag to enable fail fast when attn window is too large to fit at least one sequence in KV cache (#5974)	2025-07-25 18:10:40 -04:00
updateDecoderBuffers.cpp