kingbri 43f9483bc4 Model: Add tensor_parallel_backend option ...

This allows for users to use nccl or native depending on the GPU setup.
NCCL is only available with Linux built wheels.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>

2025-08-17 22:35:10 -04:00

..

actions.py

Downloader: log errors when downloading

2025-02-19 23:16:17 -05:00

args.py

Args: Expose api-servers to subcommands

2025-02-10 23:39:46 -05:00

auth.py

Tree: Format

2024-09-18 20:36:17 -04:00

concurrency.py

API + Model: Add blocks and checks for various load requests

2024-05-25 21:16:14 -04:00

config_models.py

Model: Add tensor_parallel_backend option

2025-08-17 22:35:10 -04:00

downloader.py

Downloader: Switch to use API sizes

2025-06-30 12:49:53 -04:00

gen_logging.py

API: Add timings to usage stats

2025-06-17 22:54:51 -04:00

hardware.py

Common: Add hardware file

2025-05-02 21:33:25 -04:00

health.py

Add health check monitoring for EXL2 errors (#206)

2024-09-22 21:40:36 -04:00

image_util.py

Common: Refactor get_image to common functions

2025-06-15 19:20:36 +02:00

logger.py

FIx logs path

2025-04-22 21:14:45 -04:00

model.py

API + Model: Fix application of defaults

2025-07-03 14:37:34 -04:00

multimodal.py

Tree: Format

2025-06-15 19:33:14 +02:00

networking.py

remove unused imports

2024-09-11 18:00:29 +01:00

optional_dependencies.py

Dependencies: Fix unsupported dependency error

2025-06-13 14:57:02 -04:00

sampling.py

Sampling: Make add_bos_token override concise

2025-05-10 19:07:35 -04:00

signals.py

Signals: Split signal handler between sync and async

2024-09-19 23:31:29 -04:00

tabby_config.py

API + Model: Fix application of defaults

2025-07-03 14:37:34 -04:00

templating.py

Templating: Support chat_template.jinja

2025-08-03 16:10:08 -07:00

transformers_utils.py

Model: Default max_seq_len to 4096

2025-06-13 14:57:24 -04:00

utils.py

Config: Deep merge model overrides

2025-07-03 12:17:09 -04:00