huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-05-24 12:32:11 +00:00
Code Issues Packages Projects Releases Wiki Activity
d658b5def3
text-generation-inference/backends/gaudi/server/text_generation_server/utils
History
Wang, Yi d658b5def3
Deepseek R1 for Gaudi backend (#3211) 
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
2025-05-19 16:36:39 +02:00
..
merges Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
__init__.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
adapter.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
chunks.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
convert.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
debug.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
dist.py Deepseek R1 for Gaudi backend (#3211) 2025-05-19 16:36:39 +02:00
hub.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
import_utils.py Deepseek R1 for Gaudi backend (#3211) 2025-05-19 16:36:39 +02:00
kernels.py Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113) 2025-04-14 15:58:13 +02:00
log.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
logits_process.py Hotfix gaudi2 with newer transformers. (#3176) 2025-04-15 12:39:28 +02:00
peft.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
prefill_chunking.py Gaudi: clean cuda/rocm code in hpu backend, enable flat_hpu (#3113) 2025-04-14 15:58:13 +02:00
quantization.py Deepseek R1 for Gaudi backend (#3211) 2025-05-19 16:36:39 +02:00
segments.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
sgmv.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
speculate.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
tokens.py forward and tokenize chooser use the same shape (#3196) 2025-05-06 10:49:32 +02:00
version.py Enable Llama4 for Gaudi backend (#3223) 2025-05-15 14:35:37 +02:00
watermark.py Add Gaudi Backend (#3055) 2025-02-28 12:14:58 +01:00
weights.py Deepseek R1 for Gaudi backend (#3211) 2025-05-19 16:36:39 +02:00