Deprecations for v0.23 and v0.24 (#44992)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
+1
-3
@@ -3,6 +3,4 @@
|
||||
model_name: "openai/gpt-oss-20b"
|
||||
metric_threshold: 0.568
|
||||
reasoning_effort: "low"
|
||||
server_args: "--tensor-parallel-size 2"
|
||||
env:
|
||||
VLLM_USE_FLASHINFER_MOE_MXFP4_BF16: "1"
|
||||
server_args: "--tensor-parallel-size 2 --moe-backend flashinfer_cutlass"
|
||||
@@ -0,0 +1,6 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
model_name: "openai/gpt-oss-20b"
|
||||
metric_threshold: 0.568
|
||||
reasoning_effort: "low"
|
||||
server_args: "--tensor-parallel-size 2 --moe-backend flashinfer_trtllm"
|
||||
@@ -3,6 +3,4 @@
|
||||
model_name: "openai/gpt-oss-20b"
|
||||
metric_threshold: 0.568
|
||||
reasoning_effort: "low"
|
||||
server_args: "--tensor-parallel-size 2"
|
||||
env:
|
||||
VLLM_MXFP4_USE_MARLIN: "1"
|
||||
server_args: "--tensor-parallel-size 2 --moe-backend marlin --linear-backend marlin"
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
# B200 model configurations for GPQA evaluation
|
||||
# Tests different environment variable combinations
|
||||
gpt-oss-20b-flashinfer-mxfp4-bf16.yaml
|
||||
gpt-oss-20b-flashinfer-mxfp4-bf16-trtllm.yaml
|
||||
gpt-oss-20b-flashinfer-mxfp4-mxfp8-cutlass.yaml
|
||||
gpt-oss-20b-sm100-fi-mxfp4-mxfp8-trtllm.yaml
|
||||
@@ -1,5 +1,5 @@
|
||||
# H100 model configurations for GPQA evaluation
|
||||
# Tests different environment variable combinations
|
||||
gpt-oss-20b-baseline.yaml
|
||||
gpt-oss-20b-flashinfer-mxfp4-bf16.yaml
|
||||
gpt-oss-20b-flashinfer-mxfp4-bf16-cutlass.yaml
|
||||
gpt-oss-20b-marlin.yaml
|
||||
|
||||
@@ -30,9 +30,9 @@ model_name: "Qwen/Qwen2.5-1.5B-Instruct"
|
||||
accuracy_threshold: 0.54 # Minimum expected accuracy
|
||||
num_questions: 1319 # Number of questions (default: full test set)
|
||||
num_fewshot: 5 # Few-shot examples from train set
|
||||
server_args: "--max-model-len 4096 --tensor-parallel-size 2" # Server arguments
|
||||
server_args: "--max-model-len 4096 --tensor-parallel-size 2 --moe-backend flashinfer_cutlass" # Server arguments
|
||||
env: # Environment variables (optional)
|
||||
VLLM_USE_FLASHINFER_MOE_FP4: "1"
|
||||
VLLM_LOGGING_LEVEL: "DEBUG"
|
||||
```
|
||||
|
||||
The `server_args` field accepts any arguments that can be passed to `vllm serve`.
|
||||
|
||||
Reference in New Issue
Block a user