| .. |
|
custom_modeling
|
add intel xpu support for TGI (#1475)
|
2024-06-10 13:16:45 +03:00 |
|
__init__.py
|
Updated kv cache for starcoder (#128)
|
2024-06-14 22:36:44 +02:00 |
|
bloom.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-04-25 09:13:03 +03:00 |
|
cache_manager.py
|
add intel xpu support for TGI (#1475)
|
2024-06-10 13:16:45 +03:00 |
|
causal_lm.py
|
Removed redundant and crash causing regions to be a subject to Torch compile (#194)
|
2024-08-08 13:06:20 +02:00 |
|
flash_causal_lm.py
|
Dummy CI run. (#1817)
|
2024-06-10 13:57:59 +03:00 |
|
flash_cohere.py
|
fix: fix CohereForAI/c4ai-command-r-plus (#1707)
|
2024-04-25 17:51:35 +03:00 |
|
flash_dbrx.py
|
feat: Add dbrx support (#1685)
|
2024-04-25 14:07:28 +03:00 |
|
flash_gemma.py
|
feat: cohere (#1660)
|
2024-04-25 12:39:14 +03:00 |
|
flash_llama.py
|
Dummy CI run. (#1817)
|
2024-06-10 13:57:59 +03:00 |
|
flash_mistral.py
|
Integrate flash attention for starcoder2 tgi through habana and some fixes, enabling (#198)
|
2024-08-07 22:06:05 +02:00 |
|
flash_mixtral.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-04-25 09:13:03 +03:00 |
|
flash_neox.py
|
Dummy CI run. (#1817)
|
2024-06-10 13:57:59 +03:00 |
|
flash_phi.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-04-25 09:13:03 +03:00 |
|
flash_qwen2.py
|
Fixing qwen2. (#1818)
|
2024-06-10 13:57:52 +03:00 |
|
flash_rw.py
|
Dummy CI run. (#1817)
|
2024-06-10 13:57:59 +03:00 |
|
flash_santacoder.py
|
Dummy CI run. (#1817)
|
2024-06-10 13:57:59 +03:00 |
|
flash_starcoder2.py
|
feat: Qwen2 (#1608)
|
2024-04-25 09:21:22 +03:00 |
|
galactica.py
|
feat: Qwen2 (#1608)
|
2024-04-25 09:21:22 +03:00 |
|
globals.py
|
Small CI cleanup. (#1801)
|
2024-06-10 14:01:01 +03:00 |
|
gpt_neox.py
|
feat: Qwen2 (#1608)
|
2024-04-25 09:21:22 +03:00 |
|
idefics2.py
|
Idefics2. (#1756)
|
2024-06-10 09:29:08 +03:00 |
|
idefics_causal_lm.py
|
Adding Llava-Next (Llava 1.6) with full support. (#1709)
|
2024-04-25 14:30:55 +00:00 |
|
idefics.py
|
Fix idefics default. (#1614)
|
2024-04-25 10:12:13 +03:00 |
|
llava_next.py
|
Idefics2. (#1756)
|
2024-06-10 09:29:08 +03:00 |
|
mamba.py
|
Make --cuda-graphs work as expected (bis) (#1768)
|
2024-06-10 09:24:43 +03:00 |
|
model.py
|
Use the generation config. (#1808)
|
2024-06-10 09:53:00 +03:00 |
|
mpt.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-04-25 09:13:03 +03:00 |
|
opt.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-04-25 09:13:03 +03:00 |
|
phi.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-04-25 09:13:03 +03:00 |
|
rw.py
|
feat: Qwen2 (#1608)
|
2024-04-25 09:21:22 +03:00 |
|
santacoder.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-04-25 09:13:03 +03:00 |
|
seq2seq_lm.py
|
feat: Qwen2 (#1608)
|
2024-04-25 09:21:22 +03:00 |
|
starcoder.py
|
Updated kv cache for starcoder (#128)
|
2024-06-14 22:36:44 +02:00 |
|
t5.py
|
Revamp medusa implementation so that every model can benefit. (#1588)
|
2024-04-25 09:13:03 +03:00 |
|
types.py
|
chore: add pre-commit (#1569)
|
2024-04-24 15:32:02 +03:00 |
|
vlm_causal_lm.py
|
Idefics2. (#1756)
|
2024-06-10 09:29:08 +03:00 |
