Skip to content

GitLab

Unverified Commit 0abc7948 authored by Zhengxu Chen's avatar Zhengxu Chen Committed by GitHub
Browse files

[caching] Add enable_prompt_embeds and cpu_offload_gb to compile hashes. (#29435) 


Signed-off-by: default avatarzhxchen17 <zhxchen17@fb.com>
parent 4e57c658
Show whitespace changes
Inline Side-by-side
Showing with 1 addition and 4 deletions
vllm/config/cache.py
View file @ 0abc7948
...@@ -167,8 +167,6 @@ class CacheConfig: ...@@ -167,8 +167,6 @@ class CacheConfig:
"num_gpu_blocks_override", "num_gpu_blocks_override",
"enable_prefix_caching", "enable_prefix_caching",
"prefix_caching_hash_algo", "prefix_caching_hash_algo",
# `cpu_offload_gb` does not use `torch.compile` yet.
"cpu_offload_gb",
"cpu_kvcache_space_bytes", "cpu_kvcache_space_bytes",
"mamba_page_size_padded", "mamba_page_size_padded",
# Post-init/derived counters # Post-init/derived counters
......
vllm/config/model.py
View file @ 0abc7948
...@@ -345,7 +345,6 @@ class ModelConfig: ...@@ -345,7 +345,6 @@ class ModelConfig:
"logprobs_mode", "logprobs_mode",
"disable_cascade_attn", "disable_cascade_attn",
"skip_tokenizer_init", "skip_tokenizer_init",
"enable_prompt_embeds",
"served_model_name", "served_model_name",
"config_format", "config_format",
"hf_token", "hf_token",
......
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