squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Misc] Fix some help info of arg_utils to improve readability (#10362)

Browse Source
This commit is contained in:
shangmingc 2024-11-15 20:40:30 +08:00 committed by GitHub
parent 1d65ec7eeb
commit f2056f726d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
vllm/engine/arg_utils.py
View File

@ -272,10 +272,10 @@ class EngineArgs:
parser.add_argument(
'--allowed-local-media-path',
type=str,
help="Allowing API requests to read local images or videos"
"from directories specified by the server file system."
"This is a security risk."
"Should only be enabled in trusted environments")
help="Allowing API requests to read local images or videos "
"from directories specified by the server file system. "
"This is a security risk. "
"Should only be enabled in trusted environments.")
parser.add_argument('--download-dir',
type=nullable_str,
default=EngineArgs.download_dir,
@ -340,7 +340,7 @@ class EngineArgs:
'scaling factors. This should generally be supplied, when '
'KV cache dtype is FP8. Otherwise, KV cache scaling factors '
'default to 1.0, which may cause accuracy issues. '
'FP8_E5M2 (without scaling) is only supported on cuda version'
'FP8_E5M2 (without scaling) is only supported on cuda version '
'greater than 11.8. On ROCm (AMD GPU), FP8_E4M3 is instead '
'supported for common inference criteria.')
parser.add_argument('--max-model-len',
@ -446,9 +446,9 @@ class EngineArgs:
'this argument can be seen as a virtual way to increase '
'the GPU memory size. For example, if you have one 24 GB '
'GPU and set this to 10, virtually you can think of it as '
'a 34 GB GPU. Then you can load a 13B model with BF16 weight,'
'a 34 GB GPU. Then you can load a 13B model with BF16 weight, '
'which requires at least 26GB GPU memory. Note that this '
'requires fast CPU-GPU interconnect, as part of the model is'
'requires fast CPU-GPU interconnect, as part of the model is '
'loaded from CPU memory to GPU memory on the fly in each '
'model forward pass.')
parser.add_argument(
@ -468,7 +468,7 @@ class EngineArgs:
type=int,
default=None,
help='If specified, ignore GPU profiling result and use this number'
'of GPU blocks. Used for testing preemption.')
' of GPU blocks. Used for testing preemption.')
parser.add_argument('--max-num-batched-tokens',
type=int,
default=EngineArgs.max_num_batched_tokens,
@ -514,7 +514,7 @@ class EngineArgs:
parser.add_argument('--hf-overrides',
type=json.loads,
default=EngineArgs.hf_overrides,
help='Extra arguments for the HuggingFace config.'
help='Extra arguments for the HuggingFace config. '
'This should be a JSON string that will be '
'parsed into a dictionary.')
parser.add_argument('--enforce-eager',
@ -572,7 +572,7 @@ class EngineArgs:
'--mm-processor-kwargs',
default=None,
type=json.loads,
help=('Overrides for the multimodal input mapping/processing,'
help=('Overrides for the multimodal input mapping/processing, '
'e.g., image processor. For example: {"num_crops": 4}.'))
# LoRA related configs
@ -822,9 +822,9 @@ class EngineArgs:
"of the provided names. The model name in the model "
"field of a response will be the first name in this "
"list. If not specified, the model name will be the "
"same as the `--model` argument. Noted that this name(s)"
"same as the `--model` argument. Noted that this name(s) "
"will also be used in `model_name` tag content of "
"prometheus metrics, if multiple names provided, metrics"
"prometheus metrics, if multiple names provided, metrics "
"tag will take the first one.")
parser.add_argument('--qlora-adapter-name-or-path',
type=str,