huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-21 23:12:07 +00:00
Code Issues Packages Projects Releases Wiki Activity
ac580f515b
text-generation-inference/server/text_generation_server/utils
History
fxmarty 4b376b30f1 GPTQ support on ROCm (#1489) 
Tested with
```
CUDA_VISIBLE_DEVICES=0 text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq
EXLLAMA_VERSION=1 CUDA_VISIBLE_DEVICES=0 text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq
CUDA_VISIBLE_DEVICES="0,1" text-generation-launcher --model-id TheBloke/Llama-2-7B-Chat-GPTQ --quantize gptq
```

all with good and identical results on MI210.

---------

Co-authored-by: Felix Marty <felix@hf.co>
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
Co-authored-by: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com>
2024-04-22 15:38:50 +03:00
..
awq/quantize feat: format code (#1070) 2023-09-27 12:22:09 +02:00
gptq GPTQ support on ROCm (#1489) 2024-04-22 15:38:50 +03:00
__init__.py Add Habana copyright header (#122) 2024-04-08 18:06:21 +02:00
convert.py fit for baichuan models (#981) 2023-09-08 16:51:34 +02:00
debug.py Add Habana copyright header (#122) 2024-04-08 18:06:21 +02:00
dist.py Add changes from Optimum Habana's TGI folder 2023-12-05 11:12:16 +01:00
flash_attn.py Fix missing make target platform for local install: 'install-flash-attention-v2' (#1414) 2024-04-22 09:18:00 +03:00
hub.py Fix local load for peft (#1373) 2024-04-22 09:03:34 +03:00
import_utils.py Add RoCm support (#1243) 2023-11-27 14:08:12 +01:00
layers.py GPTQ support on ROCm (#1489) 2024-04-22 15:38:50 +03:00
log.py v1.3.4 2024-04-22 09:08:34 +03:00
logits_process.py Add changes from Optimum Habana's TGI folder 2023-12-05 11:12:16 +01:00
medusa.py chore: formatting 2024-04-18 16:26:00 +03:00
paged_attention.py chore: formatting 2024-04-18 16:26:00 +03:00
peft.py fix: fix local loading for .bin models (#1419) 2024-04-22 09:17:52 +03:00
speculate.py chore: formatting 2024-04-18 16:26:00 +03:00
tokens.py fix: only keep stop sequence buffer if we have some 2024-04-19 14:18:00 +03:00
watermark.py Add changes from Optimum Habana's TGI folder 2023-12-05 11:12:16 +01:00
weights.py Fixing non divisible embeddings. (#1476) 2024-04-22 12:48:59 +03:00