Skip to content

Commit 51867fe

Browse files
dtrifirodtrifiro
committed
cleanup configs
1 parent c032e04 commit 51867fe

File tree

13 files changed

+60
-3
lines changed

13 files changed

+60
-3
lines changed

‎Qwen/Qwen2.5-7B-Instruct/accuracy/server-rocm.yml

Lines changed: 6 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1-
gpu_memory_utilization: 0.6
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
6+
gpu_memory_utilization: 0.8

‎RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8-dynamic/accuracy/server-rocm.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
16
gpu_memory_utilization: 0.6

‎RedHatAI/Mistral-Small-24B-Instruct-2501-FP8-Dynamic/accuracy/server-rocm.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
16
gpu_memory_utilization: 0.8

‎RedHatAI/Mistral-Small-24B-Instruct-2501-quantized.w8a8/accuracy/server-rocm.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
16
gpu_memory_utilization: 0.8

‎RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic/accuracy/server-rocm.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
16
gpu_memory_utilization: 0.6

‎RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w8a8/accuracy/server-rocm.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
16
gpu_memory_utilization: 0.6

‎RedHatAI/Qwen2.5-7B-Instruct-FP8-dynamic/accuracy/server-rocm.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
16
gpu_memory_utilization: 0.6

‎RedHatAI/phi-4-FP8-dynamic/accuracy/server-rocm.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
16
gpu_memory_utilization: 0.6

‎ibm-granite/granite-3.1-8b-instruct/accuracy/server-rocm.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1 +1,6 @@
1+
# common/accuracy/server.yml
2+
trust-remote-code: true
3+
tensor-parallel-size: 1
4+
max-model-len: 16384
5+
# override
16
gpu_memory_utilization: 0.6

‎meta-llama/Llama-3.1-8B-Instruct/accuracy/server-rocm.yml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,6 @@
1+
# common/accuracy/server.yml
12
trust-remote-code: true
23
tensor-parallel-size: 1
34
max-model-len: 16384
5+
# override
46
gpu_memory_utilization: 0.6

0 commit comments

Comments
 (0)