cjw/amd-r9700-vllm-toolboxes
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

x

Browse Source
This commit is contained in:
SZCJW
2026-03-29 04:24:28 +08:00
parent 6e8990acd1
commit 9f128486de
1 changed files with 25 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config.json
+25 -19
View File
@@ -1,5 +1,5 @@
{ {
"default_model": "Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit", "default_model": "Qwen3.5-35B-A3B-GPTQ-Int4",
"models": { "models": {
"Meta-Llama-3.1-8B-Instruct": { "Meta-Llama-3.1-8B-Instruct": {
"ctx": "65536", "ctx": "65536",
@@ -8,6 +8,9 @@
"max_num_seqs": "64", "max_num_seqs": "64",
"max_tokens": "32768", "max_tokens": "32768",
"gpu_util": "0.98", "gpu_util": "0.98",
"tool_call_parser": "qwen3_xml",
"enable_auto_tool_choice": true,
"served_model_name": "Meta-Llama-3.1-8B-Instruct",
"hf_model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct" "hf_model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct"
}, },
"gpt-oss-20b": { "gpt-oss-20b": {
@@ -17,6 +20,9 @@
"max_num_seqs": "64", "max_num_seqs": "64",
"max_tokens": "8192", "max_tokens": "8192",
"gpu_util": "0.98", "gpu_util": "0.98",
"tool_call_parser": "qwen3_xml",
"enable_auto_tool_choice": true,
"served_model_name": "gpt-oss-20b",
"hf_model_id": "openai/gpt-oss-20b" "hf_model_id": "openai/gpt-oss-20b"
}, },
"Qwen3-14B-FP8-dynamic": { "Qwen3-14B-FP8-dynamic": {
@@ -26,6 +32,9 @@
"max_num_seqs": "64", "max_num_seqs": "64",
"max_tokens": "32768", "max_tokens": "32768",
"gpu_util": "0.98", "gpu_util": "0.98",
"tool_call_parser": "qwen3_xml",
"enable_auto_tool_choice": true,
"served_model_name": "Qwen3-14B-FP8-dynamic",
"hf_model_id": "RedHatAI/Qwen3-14B-FP8-dynamic" "hf_model_id": "RedHatAI/Qwen3-14B-FP8-dynamic"
}, },
"Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit": { "Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit": {
@@ -61,6 +70,9 @@
"max_num_seqs": "32", "max_num_seqs": "32",
"max_tokens": "29000", "max_tokens": "29000",
"gpu_util": "0.94", "gpu_util": "0.94",
"tool_call_parser": "qwen3_xml",
"enable_auto_tool_choice": true,
"served_model_name": "gemma-3-27b-it-FP8-dynamic",
"hf_model_id": "RedHatAI/gemma-3-27b-it-FP8-dynamic" "hf_model_id": "RedHatAI/gemma-3-27b-it-FP8-dynamic"
}, },
"gemma-3-12b-it-FP8-dynamic": { "gemma-3-12b-it-FP8-dynamic": {
@@ -70,26 +82,11 @@
"max_num_seqs": "64", "max_num_seqs": "64",
"max_tokens": "9900", "max_tokens": "9900",
"gpu_util": "0.98", "gpu_util": "0.98",
"tool_call_parser": "qwen3_xml",
"enable_auto_tool_choice": true,
"served_model_name": "gemma-3-12b-it-FP8-dynamic",
"hf_model_id": "RedHatAI/gemma-3-12b-it-FP8-dynamic" "hf_model_id": "RedHatAI/gemma-3-12b-it-FP8-dynamic"
}, },
"DeepSeek-R1-Distill-Qwen-14B": {
"ctx": "32768",
"trust_remote": true,
"valid_tp": [1],
"max_num_seqs": "64",
"max_tokens": "32768",
"gpu_util": "0.98",
"hf_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
},
"DeepSeek-R1-Distill-Qwen-32B-AWQ": {
"ctx": "24576",
"trust_remote": true,
"valid_tp": [1, 2],
"max_num_seqs": "64",
"max_tokens": "32768",
"gpu_util": "0.98",
"hf_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B-AWQ"
},
"GLM-4.7-Flash-AWQ": { "GLM-4.7-Flash-AWQ": {
"ctx": "32768", "ctx": "32768",
"trust_remote": true, "trust_remote": true,
@@ -97,6 +94,9 @@
"max_num_seqs": "64", "max_num_seqs": "64",
"max_tokens": "32768", "max_tokens": "32768",
"gpu_util": "0.98", "gpu_util": "0.98",
"tool_call_parser": "qwen3_xml",
"enable_auto_tool_choice": true,
"served_model_name": "GLM-4.7-Flash-AWQ",
"hf_model_id": "THUDM/GLM-4.7-Flash-AWQ" "hf_model_id": "THUDM/GLM-4.7-Flash-AWQ"
}, },
"Qwen3.5-35B-A3B-GPTQ-Int4": { "Qwen3.5-35B-A3B-GPTQ-Int4": {
@@ -106,6 +106,9 @@
"max_num_seqs": "64", "max_num_seqs": "64",
"max_tokens": "32768", "max_tokens": "32768",
"gpu_util": "0.98", "gpu_util": "0.98",
"tool_call_parser": "qwen3_xml",
"enable_auto_tool_choice": true,
"served_model_name": "Qwen3.5-35B-A3B-GPTQ-Int4",
"hf_model_id": "Qwen/Qwen3.5-35B-A3B-GPTQ-Int4" "hf_model_id": "Qwen/Qwen3.5-35B-A3B-GPTQ-Int4"
}, },
"Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit": { "Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit": {
@@ -115,6 +118,9 @@
"max_num_seqs": "64", "max_num_seqs": "64",
"max_tokens": "32768", "max_tokens": "32768",
"gpu_util": "0.98", "gpu_util": "0.98",
"tool_call_parser": "qwen3_xml",
"enable_auto_tool_choice": true,
"served_model_name": "Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit",
"hf_model_id": "Qwen/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit" "hf_model_id": "Qwen/Qwen3-Omni-30B-A3B-Instruct-AWQ-4bit"
} }
} }