kris1025 e2c5a38879 [https://nvbugs/5534574][fix] disable spec decoding forever once the request spec decoding is disabled (#8446) ... Signed-off-by: linquanh <linquanh@nvidia.com>		2025-10-29 19:28:43 +08:00
..
__init__.py	[None][feat] Draft: Save state first pass (#7012)	2025-10-01 18:40:55 -04:00
auto_heuristic.py	[None][feat] Clean up ngram auto mode, add max_concurrency to configs (#6676)	2025-08-07 12:51:47 -04:00
drafter.py	[TRTLLM-8160][feat] Add max_total_draft_tokens (#8366)	2025-10-21 11:11:04 -04:00
drafting_loops.py	[TRTLLM-8160][feat] Add max_total_draft_tokens (#8366)	2025-10-21 11:11:04 -04:00
eagle3.py	[None][fix] Fix MTP 2-model (#8115)	2025-10-03 10:13:50 -07:00
interface.py	[TRTLLM-8160][feat] Add max_total_draft_tokens (#8366)	2025-10-21 11:11:04 -04:00
model_drafter.py	[https://nvbugs/5534574][fix] disable spec decoding forever once the request spec decoding is disabled (#8446)	2025-10-29 19:28:43 +08:00
mtp.py	[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405)	2025-10-24 13:40:41 -04:00
ngram.py	[TRTLLM-8160][feat] Add max_total_draft_tokens (#8366)	2025-10-21 11:11:04 -04:00
save_hidden_state.py	[TRTLLM-8160][feat] Add max_total_draft_tokens (#8366)	2025-10-21 11:11:04 -04:00
spec_tree_manager.py	[TRTLLM-6393][feat] add static tree sampling and verification (#7161)	2025-09-26 13:16:16 -04:00
speculation_gate.py	[TRTLLM-7412][feat] Turn off spec decode when the rolling average acceptance length drops below threshold. (#7283)	2025-10-13 15:51:14 -07:00
utils.py	[TRTLLM-7954][feat] Target model KV cache rellocation (#8421)	2025-10-23 09:36:50 +08:00