Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
change
sglang
Commits
3ff64113
"vscode:/vscode.git/clone" did not exist on "bb185b0e926a1750dbfe806e7cc13282ed00905d"
Unverified
Commit
3ff64113
authored
Oct 07, 2024
by
Jani Monoses
Committed by
GitHub
Oct 07, 2024
Browse files
Remove references to squeezellm (#1603)
parent
2b302b93
Changes
2
Show whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
0 additions
and
3 deletions
+0
-3
python/sglang/srt/layers/quantization/__init__.py
python/sglang/srt/layers/quantization/__init__.py
+0
-2
python/sglang/srt/server_args.py
python/sglang/srt/server_args.py
+0
-1
No files found.
python/sglang/srt/layers/quantization/__init__.py
View file @
3ff64113
...
@@ -19,7 +19,6 @@ from vllm.model_executor.layers.quantization.gptq_marlin import GPTQMarlinConfig
...
@@ -19,7 +19,6 @@ from vllm.model_executor.layers.quantization.gptq_marlin import GPTQMarlinConfig
from
vllm.model_executor.layers.quantization.gptq_marlin_24
import
GPTQMarlin24Config
from
vllm.model_executor.layers.quantization.gptq_marlin_24
import
GPTQMarlin24Config
from
vllm.model_executor.layers.quantization.marlin
import
MarlinConfig
from
vllm.model_executor.layers.quantization.marlin
import
MarlinConfig
from
vllm.model_executor.layers.quantization.qqq
import
QQQConfig
from
vllm.model_executor.layers.quantization.qqq
import
QQQConfig
from
vllm.model_executor.layers.quantization.squeezellm
import
SqueezeLLMConfig
from
vllm.model_executor.layers.quantization.tpu_int8
import
Int8TpuConfig
from
vllm.model_executor.layers.quantization.tpu_int8
import
Int8TpuConfig
from
sglang.srt.layers.quantization.base_config
import
QuantizationConfig
from
sglang.srt.layers.quantization.base_config
import
QuantizationConfig
...
@@ -39,7 +38,6 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
...
@@ -39,7 +38,6 @@ QUANTIZATION_METHODS: Dict[str, Type[QuantizationConfig]] = {
"gptq_marlin"
:
GPTQMarlinConfig
,
"gptq_marlin"
:
GPTQMarlinConfig
,
"awq_marlin"
:
AWQMarlinConfig
,
"awq_marlin"
:
AWQMarlinConfig
,
"gptq"
:
GPTQConfig
,
"gptq"
:
GPTQConfig
,
"squeezellm"
:
SqueezeLLMConfig
,
"compressed-tensors"
:
CompressedTensorsConfig
,
"compressed-tensors"
:
CompressedTensorsConfig
,
"bitsandbytes"
:
BitsAndBytesConfig
,
"bitsandbytes"
:
BitsAndBytesConfig
,
"qqq"
:
QQQConfig
,
"qqq"
:
QQQConfig
,
...
...
python/sglang/srt/server_args.py
View file @
3ff64113
...
@@ -266,7 +266,6 @@ class ServerArgs:
...
@@ -266,7 +266,6 @@ class ServerArgs:
"marlin"
,
"marlin"
,
"gptq_marlin"
,
"gptq_marlin"
,
"awq_marlin"
,
"awq_marlin"
,
"squeezellm"
,
"bitsandbytes"
,
"bitsandbytes"
,
],
],
help
=
"The quantization method."
,
help
=
"The quantization method."
,
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment