Karol Damaszke 4b4382c6f8 Fix dtype mismatch in HeterogeneousFrequencyPenaltyLogitsProcessor (#163)		2024-07-03 10:57:41 +02:00
..
awq	ROCm AWQ support (#1514)	2024-04-24 09:21:34 +00:00
gptq	chore: add pre-commit (#1569)	2024-04-24 15:32:02 +03:00
__init__.py	Pad next token chooser parameters with empty logits processors (#151)	2024-05-29 22:43:56 +02:00
convert.py	Force weights_only (before fully breaking pickle files anyway). (#1710)	2024-04-25 15:10:53 +03:00
debug.py	Add Habana copyright header (#122)	2024-04-08 18:06:21 +02:00
dist.py	add intel xpu support for TGI (#1475)	2024-06-10 13:16:45 +03:00
flash_attn.py	add intel xpu support for TGI (#1475)	2024-06-10 13:16:45 +03:00
hub.py	Revamp medusa implementation so that every model can benefit. (#1588)	2024-04-25 09:13:03 +03:00
import_utils.py	Dummy CI run. (#1817)	2024-06-10 13:57:59 +03:00
layers.py	fix: use get_speculate to the number of layers (#1737)	2024-06-10 14:02:23 +03:00
log.py	v1.3.4	2024-04-22 09:08:34 +03:00
logits_process.py	Fix dtype mismatch in HeterogeneousFrequencyPenaltyLogitsProcessor (#163)	2024-07-03 10:57:41 +02:00
paged_attention.py	add intel xpu support for TGI (#1475)	2024-06-10 13:16:45 +03:00
peft.py	fix: fix local loading for .bin models (#1419)	2024-04-22 09:17:52 +03:00
speculate.py	chore: formatting	2024-04-18 16:26:00 +03:00
tokens.py	Use the generation config. (#1808)	2024-06-10 09:53:00 +03:00
watermark.py	Add changes from Optimum Habana's TGI folder	2023-12-05 11:12:16 +01:00
weights.py	Phi3 support (#1797)	2024-06-10 09:27:01 +03:00