TensorRT-LLMs/tensorrt_llm/_torch/speculative
jellysnack 99ba723e20
[None][fix] logits device and shape issues in dynamic draft path (#9079)
Signed-off-by: jellysnack <oleg.jellysnack@gmail.com>
2025-11-18 19:22:47 -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-8136][feat] Dynamic draft length in spec decode (stage 1). (#8194) 2025-11-18 11:13:39 -05:00
drafting_loops.py [None][feat] Add simple optimizations for MTP 2-model (#9176) 2025-11-17 10:05:39 -05:00
eagle3.py [None][fix] Fix MTP 2-model (#8115) 2025-10-03 10:13:50 -07:00
interface.py [None][feat] Add simple optimizations for MTP 2-model (#9176) 2025-11-17 10:05:39 -05:00
model_drafter.py [None][fix] logits device and shape issues in dynamic draft path (#9079) 2025-11-18 19:22:47 -08:00
mtp.py [None][feat] Support Glm4MoeForCausalLM (#8256) 2025-11-18 09:43:21 +08:00
ngram.py [TRTLLM-8136][feat] Dynamic draft length in spec decode (stage 1). (#8194) 2025-11-18 11:13:39 -05:00
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