TensorRT-LLMs/tests/unittest/_torch/speculative
Izzy Putterman b36460d7b5
[None][feat] Deepseek: Start Eagle work (#6210)
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
Co-authored-by: Mike Iovine <miovine@nvidia.com>
2025-08-22 12:57:17 -04:00
..
test_draft_target.py [TRTLLM-7157][feat] BREAKING CHANGE Introduce sampler_type, detect sampler according to options (#6831) 2025-08-16 00:27:24 -04:00
test_dynamic_spec_decode.py [TRTLLM-6392][feat] Support turning on/off spec decoding dynamically (#6363) 2025-07-31 15:31:39 -04:00
test_eagle3.py [None][feat] Deepseek: Start Eagle work (#6210) 2025-08-22 12:57:17 -04:00
test_kv_cache_reuse.py [TRTLLM-6452][feat]: Two-model engine KV cache reuse support (#6133) 2025-07-19 13:17:15 +08:00
test_mtp.py [refactor] Simplification of Speculative decoding configs (#5639) 2025-07-10 11:37:30 -04:00
test_ngram.py [https://nvbugs/5452167][fix] Fix ngram padding issue (#6837) 2025-08-13 11:23:16 +08:00
test_torch_rejection_sampling.py [None][feat] Add test for speculative rejection sampler (2-model) (#6542) 2025-08-13 22:09:35 -04:00
test_user_provided.py [refactor] Simplification of Speculative decoding configs (#5639) 2025-07-10 11:37:30 -04:00