biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1][Spec Decode] Remove deprecated spec decode config params (#15466)

Browse Source 
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
This commit is contained in:
shangmingc
2025-04-01 00:19:35 +08:00
committed by GitHub
parent 09e974d483
commit 239b7befdd
10 changed files with 125 additions and 220 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.buildkite/nightly-benchmarks/tests/serving-tests.json
View File

@@ -63,10 +63,12 @@
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"disable_log_requests": "",
"tensor_parallel_size": 4,
"swap_space": 16,
"speculative_model": "turboderp/Qwama-0.5B-Instruct",
"num_speculative_tokens": 4,
"speculative_draft_tensor_parallel_size": 1
"swap_space": 16,
"speculative_config": {
"model": "turboderp/Qwama-0.5B-Instruct",
"num_speculative_tokens": 4,
"draft_tensor_parallel_size": 1
}
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",