| .. |
|
custom_modeling
|
Merge branch 'main' into qwen3_moe
|
2025-05-29 13:05:31 +08:00 |
|
__init__.py
|
Merge branch 'main' into qwen3_moe
|
2025-05-29 13:05:31 +08:00 |
|
bloom.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
causal_lm.py
|
Adjust the round_up_seq logic in Gaudi backend (#3224)
|
2025-05-12 09:58:43 +02:00 |
|
flash_causal_lm.py
|
fp8 compressed tensors w8a8 support for Gaudi backend (#3242)
|
2025-05-28 14:54:20 +02:00 |
|
flash_vlm_causal_lm.py
|
Move input_ids to hpu and remove disposal of adapter_meta (#3237)
|
2025-05-22 09:21:31 +02:00 |
|
galactica.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
globals.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
idefics_causal_lm.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
mamba.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
mllama_causal_lm.py
|
Move input_ids to hpu and remove disposal of adapter_meta (#3237)
|
2025-05-22 09:21:31 +02:00 |
|
model.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
pali_gemma.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
seq2seq_lm.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
starcoder.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
types.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
vlm_causal_lm.py
|
Fix HF_HUB_OFFLINE=1 for Gaudi backend (#3193)
|
2025-05-06 10:47:53 +02:00 |
