Michal Guzek 08d57123f9 [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) ... Signed-off-by: moraxu <mguzek@nvidia.com>		2025-07-25 18:10:40 -04:00
..
memory_pools	Update TensorRT-LLM (#2820)	2025-02-25 21:21:49 +08:00
processor_wrapper	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
__init__.py	Update TensorRT-LLM (#2110)	2024-08-13 22:34:33 +08:00
enc_dec_model_runner.py	feat: [nvbugs/5261055][nvbugs/5170160] non-invasive pipeline parallelism (#4034)	2025-05-16 04:16:53 +08:00
generation.py	feat: [nvbugs/5261055][nvbugs/5170160] non-invasive pipeline parallelism (#4034)	2025-05-16 04:16:53 +08:00
kv_cache_manager.py	open source 7f370deb0090d885d7518c2b146399ba3933c004 (#2273)	2024-09-30 13:51:19 +02:00
medusa_utils.py	Update TensorRT-LLM (#2582)	2024-12-16 21:50:47 -08:00
model_runner_cpp.py	[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
model_runner.py	[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
multimodal_model_runner.py	[nvbugs/5385972][nvbugs/5387423][Fix] Minor fix for llava_next/llava_onevision (#5998)	2025-07-15 10:01:35 -04:00
redrafter_utils.py	Update TensorRT-LLM (#2582)	2024-12-16 21:50:47 -08:00
session.py	Update TensorRT-LLM (#2755)	2025-02-11 03:01:00 +00:00