| .. |
|
__init__.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
bloom_modeling.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
clip.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
flash_cohere_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_dbrx_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_deepseek_v2_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_deepseek_v3_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_gemma2_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_gemma3_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_gemma_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_gpt2_modeling.py
|
[gaudi] Perf optimization (#3256)
|
2025-06-11 15:00:21 +02:00 |
|
flash_gptj_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_llama4_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_llama_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_llava_next.py
|
[gaudi] Refine logging for Gaudi warmup (#3222)
|
2025-06-18 12:34:00 +02:00 |
|
flash_mistral_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_mixtral_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_mllama.py
|
[gaudi] Vlm rebase and issue fix in benchmark test (#3263)
|
2025-06-12 22:26:37 +02:00 |
|
flash_neox_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_pali_gemma_modeling.py
|
[gaudi] Vlm rebase and issue fix in benchmark test (#3263)
|
2025-06-12 22:26:37 +02:00 |
|
flash_phi_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_phi_moe_modeling.py
|
Deepseek R1 for Gaudi backend (#3211)
|
2025-05-19 16:36:39 +02:00 |
|
flash_qwen2_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_qwen3_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_qwen3_moe_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_rw_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
flash_santacoder_modeling.py
|
[gaudi] Perf optimization (#3256)
|
2025-06-11 15:00:21 +02:00 |
|
flash_starcoder2_modeling.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
idefics2.py
|
[gaudi] Refine logging for Gaudi warmup (#3222)
|
2025-06-18 12:34:00 +02:00 |
|
idefics3.py
|
[gaudi] Refine logging for Gaudi warmup (#3222)
|
2025-06-18 12:34:00 +02:00 |
|
mamba_modeling.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
qwen2_5_vl.py
|
[Gaudi] Remove optimum-habana (#3261)
|
2025-06-12 22:35:36 +02:00 |
|
qwen2_vl.py
|
[gaudi] Vlm rebase and issue fix in benchmark test (#3263)
|
2025-06-12 22:26:37 +02:00 |
|
siglip.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
vlm.py
|
[gaudi] gemma3 text and vlm model intial support. need to add sliding window support later (#3270)
|
2025-06-19 09:32:34 +02:00 |
