text-generation-inference/server/text_generation_server/layers
Daniël de Kok f1f98e369f
Add support for Marlin 2:4 sparsity ()
This change adds support for 2:4 sparsity when using Marlin
quantization. The 2:4 kernel is used when:

* The quantizer is `marlin`;
* the quantizer checkpoint format is `marlin_24`.

Fixes .
2024-06-25 21:09:42 +02:00
..
attention Removing IPEX_AVAIL. () 2024-06-25 13:20:57 +02:00
awq Support AWQ quantization with bias () 2024-06-25 21:09:00 +02:00
gptq Fix text-generation-server quantize () 2024-06-21 15:28:51 +02:00
__init__.py Enable multiple LoRa adapters () 2024-06-25 14:46:27 -04:00
bnb.py [Bug Fix] Update torch import reference in bnb quantization () 2024-05-15 21:08:32 +02:00
conv.py Refactor layers. () 2024-05-13 12:44:30 +02:00
eetq.py Refactor layers. () 2024-05-13 12:44:30 +02:00
exl2.py Add support for exl2 quantization 2024-05-30 11:28:05 +02:00
fp8.py Refactor layers. () 2024-05-13 12:44:30 +02:00
layernorm.py Removing IPEX_AVAIL. () 2024-06-25 13:20:57 +02:00
linear.py Add support for Marlin 2:4 sparsity () 2024-06-25 21:09:42 +02:00
lora.py Enable multiple LoRa adapters () 2024-06-25 14:46:27 -04:00
marlin.py Add support for Marlin 2:4 sparsity () 2024-06-25 21:09:42 +02:00
medusa.py fix: use path inside of speculator config () 2024-05-22 20:46:29 +02:00
mlp.py MLPSpeculator. () 2024-05-14 12:33:18 +02:00
rotary.py Removing IPEX_AVAIL. () 2024-06-25 13:20:57 +02:00
speculative.py MLPSpeculator. () 2024-05-14 12:33:18 +02:00
tensor_parallel.py Removing IPEX_AVAIL. () 2024-06-25 13:20:57 +02:00