[Refactor] refactor humming linear and moe backends to use explicit layer configs (#49610)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com> Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
co-authored by
OpenAI Codex
parent
e229fdbc87
commit
fcde8e1460
@@ -0,0 +1,9 @@
|
||||
model_name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4"
|
||||
accuracy_threshold: 0.29
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
server_args: >-
|
||||
--enforce-eager
|
||||
--max-model-len 8192
|
||||
--moe-backend humming
|
||||
--linear-backend humming
|
||||
@@ -1,5 +1,5 @@
|
||||
model_name: "nm-testing/Qwen3-4B-mixed-quant-RTN-wNaM"
|
||||
accuracy_threshold: 0.85
|
||||
accuracy_threshold: 0.78
|
||||
num_questions: 1319
|
||||
num_fewshot: 5
|
||||
server_args: >-
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
gpt-oss-20b-humming.yaml
|
||||
Qwen3-30B-A3B-Instruct-2507-quantized.w8a8-humming-act-int8.yaml
|
||||
Qwen3-30B-A3B-GPTQ-Int4-humming-act-int8.yaml
|
||||
Qwen3-30B-A3B-AWQ-humming.yaml
|
||||
|
||||
@@ -11,3 +11,4 @@ Qwen3-30B-A3B-NVFP4-humming.yaml
|
||||
Qwen3-30B-A3B-AWQ-humming.yaml
|
||||
Qwen3.5-35B-A3B-FP8-humming.yaml
|
||||
Qwen3.5-35B-A3B-experts-int8-humming.yaml
|
||||
NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4-humming.yaml
|
||||
|
||||
Reference in New Issue
Block a user