| .. |
|
__init__.py
|
[None][feat] Implement sampling for MTP 1-model (#10019)
|
2025-12-31 13:48:34 -05:00 |
|
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
|
[https://nvbugs/5772414][fix] Fix draft token tree depth=1 corner case (#10385)
|
2026-01-05 17:20:14 +01:00 |
|
eagle3.py
|
[TRTLLM-10325][feat] Refactor speculative decoding workers (#10768)
|
2026-01-21 13:05:29 -05:00 |
|
interface.py
|
[TRTLLM-10276][feat] Integrate cutedsl argmax kernel (#10476)
|
2026-01-26 22:08:47 -05:00 |
|
model_drafter.py
|
[TRTLLM-9962][feat] Some optimizations for two-model spec dec (#10208)
|
2025-12-28 12:52:04 +08:00 |
|
mtp.py
|
[TRTLLM-10312][perf] Improve performance of _write_finish_reasons in TorchSampler (#10459)
|
2026-01-29 11:06:09 -05:00 |
|
ngram.py
|
[TRTLLM-8160][feat] Add draft token tree runtime on CDL (#8586)
|
2025-11-25 09:40:55 -05:00 |
|
one_model_sampler.py
|
[None][feat] Speculative One Model: FlashInfer sampling (#10284)
|
2026-01-20 12:56:43 -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-8160][feat] Add draft token tree runtime on CDL (#8586)
|
2025-11-25 09:40:55 -05:00 |
|
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-9416][feat] Skip DS-v3.2 indexer MQA and Top-K for short sequences. (#9524)
|
2025-12-15 12:42:25 +08:00 |
