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

[V1] V1 Enablement Oracle (#13726)

Browse Source 
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
This commit is contained in:
Robert Shaw
2025-03-15 01:02:20 -04:00
committed by GitHub
parent 8c0d15d5c5
commit d4d93db2c5
96 changed files with 1537 additions and 512 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
tests/tool_use/utils.py
View File

@@ -91,20 +91,22 @@ CONFIGS: dict[str, ServerConfig] = {
"without calling a tool. DO NOT CALL A TOOL THAT IS IRRELEVANT "
"to the user's question - just respond to it normally."
},
"granite20b": {
"model":
"mbayser/granite-20b-functioncalling-FP8-KV",
"arguments": [
"--tool-call-parser", "granite-20b-fc", "--chat-template",
str(VLLM_PATH /
"examples/tool_chat_template_granite_20b_fc.jinja"),
"--max_num_seqs", "1", "--enforce-eager", "--cpu-offload-gb", "20"
],
"supports_parallel":
False,
"supports_rocm":
False,
},
# V1 Test: Passing locally but failing in CI. This runs the
# V0 Engine because of CPU offloading. Need to debug why.
# "granite20b": {
# "model":
# "mbayser/granite-20b-functioncalling-FP8-KV",
# "arguments": [
# "--tool-call-parser", "granite-20b-fc", "--chat-template",
# str(VLLM_PATH /
# "examples/tool_chat_template_granite_20b_fc.jinja"),
# "--max_num_seqs", "1", "--enforce-eager", "--cpu-offload-gb", "20"
# ],
# "supports_parallel":
# False,
# "supports_rocm":
# False,
# },
"granite-3.0-8b": {
"model":
"ibm-granite/granite-3.0-8b-instruct",