Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
88 lines
2.6 KiB
JSON
88 lines
2.6 KiB
JSON
{
|
|
"abhigoyal/vllm-medusa-llama-68m-random": {
|
|
"architectures": [
|
|
"MedusaModel"
|
|
],
|
|
"model_type": "medusa",
|
|
"text_model_type": "medusa",
|
|
"hidden_size": 768,
|
|
"total_num_hidden_layers": 1,
|
|
"total_num_attention_heads": 0,
|
|
"head_size": "Error: integer division or modulo by zero",
|
|
"vocab_size": 32000,
|
|
"total_num_kv_heads": 0,
|
|
"num_experts": 0,
|
|
"is_deepseek_mla": false,
|
|
"is_multimodal_model": false,
|
|
"dtype": "torch.float32"
|
|
},
|
|
"luccafong/deepseek_mtp_draft_random": {
|
|
"architectures": [
|
|
"DeepSeekMTPModel"
|
|
],
|
|
"model_type": "deepseek_mtp",
|
|
"text_model_type": "deepseek_mtp",
|
|
"hidden_size": 2560,
|
|
"total_num_hidden_layers": 1,
|
|
"total_num_attention_heads": 32,
|
|
"head_size": 576,
|
|
"vocab_size": 129280,
|
|
"total_num_kv_heads": 32,
|
|
"num_experts": 72,
|
|
"is_deepseek_mla": true,
|
|
"is_multimodal_model": false,
|
|
"dtype": "torch.bfloat16"
|
|
},
|
|
"eagle618/eagle-deepseek-v3-random": {
|
|
"architectures": [
|
|
"EagleDeepSeekMTPModel"
|
|
],
|
|
"model_type": "eagle",
|
|
"text_model_type": "eagle",
|
|
"hidden_size": 2560,
|
|
"total_num_hidden_layers": 1,
|
|
"total_num_attention_heads": 32,
|
|
"head_size": 576,
|
|
"vocab_size": 129280,
|
|
"total_num_kv_heads": 32,
|
|
"num_experts": 72,
|
|
"is_deepseek_mla": true,
|
|
"is_multimodal_model": false,
|
|
"dtype": "bfloat16"
|
|
},
|
|
"yuhuili/EAGLE-LLaMA3-Instruct-8B": {
|
|
"architectures": [
|
|
"EagleLlamaForCausalLM"
|
|
],
|
|
"model_type": "eagle",
|
|
"text_model_type": "eagle",
|
|
"hidden_size": 4096,
|
|
"total_num_hidden_layers": 1,
|
|
"total_num_attention_heads": 32,
|
|
"head_size": 128,
|
|
"vocab_size": 128256,
|
|
"total_num_kv_heads": 8,
|
|
"num_experts": 0,
|
|
"is_deepseek_mla": false,
|
|
"is_multimodal_model": false,
|
|
"dtype": "float16"
|
|
},
|
|
"yuhuili/EAGLE3-LLaMA3.1-Instruct-8B": {
|
|
"architectures": [
|
|
"Eagle3LlamaForCausalLM"
|
|
],
|
|
"model_type": "eagle",
|
|
"text_model_type": "eagle",
|
|
"hidden_size": 4096,
|
|
"total_num_hidden_layers": 1,
|
|
"total_num_attention_heads": 32,
|
|
"head_size": 128,
|
|
"vocab_size": 128256,
|
|
"total_num_kv_heads": 8,
|
|
"num_experts": 0,
|
|
"is_deepseek_mla": false,
|
|
"is_multimodal_model": false,
|
|
"dtype": "float16"
|
|
}
|
|
}
|