Thomas Parnell d4201e06d5

[Bugfix] Make spec. decode respect per-request seed. (#6034) ...

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>

2024-07-18 19:22:08 -07:00

..

e2e

[Bugfix] Make spec. decode respect per-request seed. (#6034)

2024-07-18 19:22:08 -07:00

__init__.py

[Speculative decoding 3/9] Worker which speculates, scores, and applies rejection sampling (#3103)

2024-03-08 23:32:46 -08:00

test_batch_expansion.py

[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) (#5602)

2024-07-01 20:10:37 -07:00

test_dynamic_spec_decode.py

[Speculative Decoding] Enabling bonus token in speculative decoding for KV cache based models (#5765)

2024-07-10 16:02:47 -07:00

test_metrics.py

[Speculative Decoding 2/2 ] Integrate typical acceptance sampler into Spec Decode Worker (#5348)

2024-07-01 00:33:05 -07:00

test_multi_step_worker.py

[Core] draft_model_runner: Implement prepare_inputs on GPU for advance_step (#6338)

2024-07-17 14:30:28 -07:00

test_ngram_worker.py

[Speculative Decoding] Enabling bonus token in speculative decoding for KV cache based models (#5765)

2024-07-10 16:02:47 -07:00

test_spec_decode_worker.py

[Speculative Decoding] Enabling bonus token in speculative decoding for KV cache based models (#5765)

2024-07-10 16:02:47 -07:00

test_utils.py

[Speculative Decoding 2/2 ] Integrate typical acceptance sampler into Spec Decode Worker (#5348)

2024-07-01 00:33:05 -07:00

utils.py

[Core] Pipeline Parallel Support (#4412)

2024-07-02 10:58:08 -07:00