2ez4bz 7ebb770dce [None][fix] Fix batching bug in Mistral3 model (#6841) ... Prior to this commit, if multiple requests with images were in the same batch, the batching logic for the images would fail. This commit fixes it, and adds unit tests for it that were verified to fail prior to the fix. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>		2025-08-14 02:15:44 -04:00
..
_torch	[None][fix] Fix batching bug in Mistral3 model (#6841)	2025-08-14 02:15:44 -04:00
api_stability	[None][opt] ADP schedule balance optimization (#6061)	2025-08-06 09:38:02 +08:00
bindings	[nvbugs/5404000] fix: waive request_perf_metrics_draft test on pre-Hopper GPUs (#6339)	2025-07-28 12:36:44 -07:00
disaggregated	feat: Dynamically remove servers in PD (#5270)	2025-06-25 09:50:04 +08:00
llmapi	[https://nvbugs/5375594][fix] fix oom issue on structural_tag test case (#6838)	2025-08-13 10:09:35 -04:00
others	test: reorganize tests folder hierarchy (#2996)	2025-03-27 12:07:53 +08:00
scaffolding	[https://nvbugs/5387375] fix(scaffolding): fix scaffolding aime test in test_e2e (#6140)	2025-07-18 10:34:37 +08:00
tools	enh: Add script to map tests <-> jenkins stages & vice-versa (#5177)	2025-07-19 00:50:40 +08:00
trt	[TRTLLM-6674][feat] (Breaking Change) Hopper SWA non-cyclic kernels + KV reuse + Spec Dec (#6379)	2025-08-05 07:47:41 +00:00
utils	[TRTLLM-6683][feat] Support LoRA reload CPU cache evicted adapter (#6786)	2025-08-11 14:31:39 -04:00
conftest.py	[TRTLLM-5508][feat] check input tokens + improve error handling (#5170)	2025-08-05 18:27:43 +01:00
dump_checkpoint_stats.py	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
gc_utils.py	[nvbug 5273941] fix: broken cyclic reference detect (#5417)	2025-07-01 20:12:55 +08:00
profile_utils.py	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
pytest.ini	[ci] parallelize torch unittests (#5714)	2025-07-09 11:05:57 +03:00
test_model_runner_cpp.py	Update TensorRT-LLM (#2936)	2025-03-18 21:25:19 +08:00
test_pip_install.py	[None][infra] Avoid intermittent access broken to nvcr.io (#6715)	2025-08-12 11:48:59 +08:00