| .. |
|
custom_modeling
|
Hotfixing qwen2 and starcoder2 (which also get clamping). (#2167)
|
2024-07-02 14:26:47 +02:00 |
|
__init__.py
|
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. (#1940)
|
2024-07-01 23:28:00 +02:00 |
|
bloom.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
causal_lm.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
flash_causal_lm.py
|
Fixing graph capture for flash decoding. (#2163)
|
2024-07-02 11:43:07 +02:00 |
|
flash_cohere.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
flash_dbrx.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
flash_gemma.py
|
refine get xpu free memory/enable Qwen2/gemma2/gemma/phi in intel platform (#2132)
|
2024-07-01 14:32:54 +02:00 |
|
flash_gemma2.py
|
refine get xpu free memory/enable Qwen2/gemma2/gemma/phi in intel platform (#2132)
|
2024-07-01 14:32:54 +02:00 |
|
flash_gpt2.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
flash_llama.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
flash_mistral.py
|
fix AttributeError: 'MixtralLayer' object has no attribute 'mlp' (#2123)
|
2024-07-01 14:17:22 +02:00 |
|
flash_mixtral.py
|
MLPSpeculator. (#1865)
|
2024-05-14 12:33:18 +02:00 |
|
flash_neox.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
flash_phi.py
|
refine get xpu free memory/enable Qwen2/gemma2/gemma/phi in intel platform (#2132)
|
2024-07-01 14:32:54 +02:00 |
|
flash_qwen2.py
|
refine get xpu free memory/enable Qwen2/gemma2/gemma/phi in intel platform (#2132)
|
2024-07-01 14:32:54 +02:00 |
|
flash_rw.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
flash_santacoder.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
flash_starcoder2.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
galactica.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
globals.py
|
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel. (#1940)
|
2024-07-01 23:28:00 +02:00 |
|
gpt_neox.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
idefics.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
idefics2.py
|
MLPSpeculator. (#1865)
|
2024-05-14 12:33:18 +02:00 |
|
idefics_causal_lm.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
llava_next.py
|
MLPSpeculator. (#1865)
|
2024-05-14 12:33:18 +02:00 |
|
mamba.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
model.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
mpt.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
opt.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
pali_gemma.py
|
Idefics2: sync added image tokens with transformers (#2080)
|
2024-06-27 15:54:35 +02:00 |
|
phi.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
rw.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
santacoder.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
seq2seq_lm.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
t5.py
|
Enable multiple LoRa adapters (#2010)
|
2024-06-25 14:46:27 -04:00 |
|
types.py
|
chore: add pre-commit (#1569)
|
2024-02-16 11:58:58 +01:00 |
|
vlm_causal_lm.py
|
Idefics2: sync added image tokens with transformers (#2080)
|
2024-06-27 15:54:35 +02:00 |
0759ec495e