| .. |
|
custom_modeling
|
feat: Add dbrx support (#1685)
|
2024-03-29 18:49:36 +01:00 |
|
__init__.py
|
feat: Add dbrx support (#1685)
|
2024-03-29 18:49:36 +01:00 |
|
bloom.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
cache_manager.py
|
feat: add mistral model (#1071)
|
2023-09-28 09:55:47 +02:00 |
|
causal_lm.py
|
feat: Qwen2 (#1608)
|
2024-02-28 15:50:31 +01:00 |
|
flash_causal_lm.py
|
Add cuda graphs sizes and make it default. (#1703)
|
2024-04-04 23:01:56 +02:00 |
|
flash_cohere.py
|
Fixing cohere tokenizer. (#1697)
|
2024-04-05 16:44:19 +02:00 |
|
flash_dbrx.py
|
feat: Add dbrx support (#1685)
|
2024-03-29 18:49:36 +01:00 |
|
flash_gemma.py
|
feat: cohere (#1660)
|
2024-03-22 17:59:25 +01:00 |
|
flash_llama.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
flash_mistral.py
|
fix: LlamaTokenizerFast to AutoTokenizer at flash_mistral.py (#1637)
|
2024-03-22 17:13:13 +01:00 |
|
flash_mixtral.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
flash_neox.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
flash_phi.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
flash_qwen2.py
|
feat: Qwen2 (#1608)
|
2024-02-28 15:50:31 +01:00 |
|
flash_rw.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
flash_santacoder.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
flash_starcoder2.py
|
feat: Qwen2 (#1608)
|
2024-02-28 15:50:31 +01:00 |
|
galactica.py
|
feat: Qwen2 (#1608)
|
2024-02-28 15:50:31 +01:00 |
|
globals.py
|
Add cuda graphs sizes and make it default. (#1703)
|
2024-04-04 23:01:56 +02:00 |
|
gpt_neox.py
|
feat: Qwen2 (#1608)
|
2024-02-28 15:50:31 +01:00 |
|
idefics.py
|
Fix idefics default. (#1614)
|
2024-02-29 13:16:34 +01:00 |
|
idefics_causal_lm.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
mamba.py
|
Add cuda graphs sizes and make it default. (#1703)
|
2024-04-04 23:01:56 +02:00 |
|
model.py
|
fix: fix logic if sliding window key is not present in config (#1352)
|
2023-12-15 14:56:17 +01:00 |
|
mpt.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
opt.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
phi.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
rw.py
|
feat: Qwen2 (#1608)
|
2024-02-28 15:50:31 +01:00 |
|
santacoder.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
seq2seq_lm.py
|
feat: Qwen2 (#1608)
|
2024-02-28 15:50:31 +01:00 |
|
t5.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-02-26 19:49:28 +01:00 |
|
types.py
|
chore: add pre-commit (#1569)
|
2024-02-16 11:58:58 +01:00 |
f9958ee191