"...git@developer.sourcefind.cn:2222/OpenDAS/vllm_cscc.git" did not exist on "e31446b6c8d887cdca031abf8527555adee46058"
Unverified Commit 8e1fd5ba authored by Matthew Bonanni's avatar Matthew Bonanni Committed by GitHub
Browse files

[CI] Bump `num_speculative_tokens` to 3 in nightly DeepSeek tests (#35882)


Signed-off-by: default avatarMatthew Bonanni <mbonanni@redhat.com>
parent ae88468b
...@@ -8,4 +8,4 @@ server_args: >- ...@@ -8,4 +8,4 @@ server_args: >-
--max-model-len 4096 --max-model-len 4096
--data-parallel-size 8 --data-parallel-size 8
--enable-expert-parallel --enable-expert-parallel
--speculative-config '{"method":"mtp","num_speculative_tokens":1}' --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
...@@ -8,4 +8,4 @@ server_args: >- ...@@ -8,4 +8,4 @@ server_args: >-
--max-model-len 4096 --max-model-len 4096
--tensor-parallel-size 8 --tensor-parallel-size 8
--enable-expert-parallel --enable-expert-parallel
--speculative-config '{"method":"mtp","num_speculative_tokens":1}' --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
...@@ -8,4 +8,4 @@ server_args: >- ...@@ -8,4 +8,4 @@ server_args: >-
--max-model-len 4096 --max-model-len 4096
--data-parallel-size 8 --data-parallel-size 8
--enable-expert-parallel --enable-expert-parallel
--speculative-config '{"method":"mtp","num_speculative_tokens":1}' --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
...@@ -8,4 +8,4 @@ server_args: >- ...@@ -8,4 +8,4 @@ server_args: >-
--max-model-len 4096 --max-model-len 4096
--tensor-parallel-size 8 --tensor-parallel-size 8
--enable-expert-parallel --enable-expert-parallel
--speculative-config '{"method":"mtp","num_speculative_tokens":1}' --speculative-config '{"method":"mtp","num_speculative_tokens":3}'
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment