3 Commits

Author	SHA1	Message	Date
Robin Kobus	72057a0a64	[TRTLLM-3429] feat: Overlap scheduling in C++ runtime (#3625) ... * disable overlap in encoder Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: invokeGatherBatch Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: overlap same batch Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * chore: add enableTrtOverlap to ExecutorConfig Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * disable overlap for beam search and spec decode Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * skip overlap tests with beam search or speculative decoding Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * moveFinishedContextRequestsToGeneration and skip unfinished requests in updateRequests Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * enable overlap in GptChunkedLongContextTests Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Enable overlap in gptManagerBenchmark Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Improve early exit Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * refactor: Use OptionalRef for newOutputTokens tensor Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * feat: Add overlap scheduling support to TRTLLMDecoder - Updated TRTLLMDecoder to accept an `enable_overlap_scheduler` parameter. - Modified the decoder's internal logic to utilize the overlap scheduling feature. - Adjusted the sequence lengths handling to ensure compatibility with the new scheduling approach. - Enhanced unit tests to include cases for the overlap scheduler with the TRTLLMDecoder. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> * fix: allNewTokens in PP Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com> --------- Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>	2025-05-06 15:06:46 +02:00
Netanel Haber	da0b0e0ee3	fix: disable kv cache reuse when minimum window size is reached, instead of maximum window size (#2983) ... * fix variable window size reuse - disable when *min attention window* starts sliding, not max * isPreCyclic -> isCyclic, and invert logic, for clarity * getDecoderState() Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>	2025-03-24 22:49:52 +08:00
Kaiyu Xie	9b931c0f63	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00