lty dee00d0de3 [Usability]local_buffer_size support for units: GB, MB, KB, B (#4829) ...

What this PR does / why we need it?
Improve usability，local_buffer_size support for units: GB, MB, KB, B,
For example, "2GB"
{
    "local_hostname": "XXX.XXX.XXX.XXX",
    "metadata_server": "P2PHANDSHAKE",
    "protocol": "ascend",
    "device_name": "",
    "use_ascend_direct": true,
    "master_server_address": "XXX.XXX.XXX.XXX:50088",
    "global_segment_size": 60000000000,
    "local_buffer_size": "2GB"
}

Does this PR introduce any user-facing change?
local_buffer_size support for units: GB, MB, KB, B

How was this patch tested?
Mooncake configures local_buffer_size as GB, MB, KB, B
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: lty <linxianchong1@huawei.com>

2025-12-09 17:52:24 +08:00

..

__init__.py

[Feature][main]reconstruction kvpool connector to ascend connector (#4438)

2025-11-28 18:08:37 +08:00

backend.py

[Feature][main]reconstruction kvpool connector to ascend connector (#4438)

2025-11-28 18:08:37 +08:00

memcache_backend.py

upgrade vLLM to main (#4608)

2025-12-02 22:10:52 +08:00

mooncake_backend.py

[Usability]local_buffer_size support for units: GB, MB, KB, B (#4829)

2025-12-09 17:52:24 +08:00