oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-07 23:53:40 +00:00
Code Issues Projects Releases Packages Wiki Activity

Remove obsolete DeepSpeed inference code (2023 relic)

Browse source
This commit is contained in:
oobabooga 2026-03-04 17:20:34 -08:00
parent 942ff8fcb4
commit 387cf9d8df
7 changed files with 2 additions and 165 deletions
Download patch file Download diff file Expand all files Collapse all files

6
modules/shared.py
View file

@ -144,12 +144,6 @@ group.add_argument('--num_experts_per_token', type=int, default=2, metavar='N',
group = parser.add_argument_group('TensorRT-LLM')
group.add_argument('--cpp-runner', action='store_true', help='Use the ModelRunnerCpp runner, which is faster than the default ModelRunner but doesn\'t support streaming yet.')
# DeepSpeed
group = parser.add_argument_group('DeepSpeed')
group.add_argument('--deepspeed', action='store_true', help='Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.')
group.add_argument('--nvme-offload-dir', type=str, help='DeepSpeed: Directory to use for ZeRO-3 NVME offloading.')
group.add_argument('--local_rank', type=int, default=0, help='DeepSpeed: Optional argument for distributed setups.')
# RoPE
group = parser.add_argument_group('RoPE')
group.add_argument('--alpha_value', type=float, default=1, help='Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.')