| .. |
|
attention
|
[gaudi] Gemma3 sliding window support (#3280)
|
2025-07-01 10:06:01 +02:00 |
|
awq
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
compressed_tensors
|
fp8 compressed tensors w8a8 support for Gaudi backend (#3242)
|
2025-05-28 14:54:20 +02:00 |
|
gptq
|
Gaudi gptq gidx support (#3297)
|
2025-07-17 16:00:12 +02:00 |
|
moe
|
[gaudi] Deepseek v2 mla and add ep to unquantized moe (#3287)
|
2025-07-07 11:29:39 +02:00 |
|
__init__.py
|
Deepseek R1 for Gaudi backend (#3211)
|
2025-05-19 16:36:39 +02:00 |
|
bnb.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
conv.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
exl2.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
fp8.py
|
fp8 compressed tensors w8a8 support for Gaudi backend (#3242)
|
2025-05-28 14:54:20 +02:00 |
|
layernorm.py
|
Deepseek R1 for Gaudi backend (#3211)
|
2025-05-19 16:36:39 +02:00 |
|
linear.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
|
lora.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
medusa.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
mlp.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
rotary.py
|
[gaudi] Refine rope memory, do not need to keep sin/cos cache per layer (#3274)
|
2025-06-23 11:15:39 +02:00 |
|
speculative.py
|
Add Gaudi Backend (#3055)
|
2025-02-28 12:14:58 +01:00 |
|
tensor_parallel.py
|
Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113)
|
2025-04-14 15:58:13 +02:00 |
