-
Notifications
You must be signed in to change notification settings - Fork 77
feat: build deepseek v2 decoder layer and related model files for mlu device. #373
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
xllm/models/llm/mlu/deepseek_v2.h
Outdated
| int32_t dp_local_tp_size_; | ||
| int32_t num_experts_per_tok_; | ||
| int32_t num_speculative_tokens_ = 0; | ||
| at::Device device_; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
use torch::
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I have removed those useless variables due to my unwary copying from xllm/models/llm/deepseek_v2.h
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
fixed
xllm/models/llm/mlu/deepseek_v2.h
Outdated
| #include <gflags/gflags.h> | ||
| #include <torch/torch.h> | ||
|
|
||
| #include <boost/algorithm/string.hpp> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
remove this line
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
removed
|
|
||
| #include <torch/torch.h> | ||
|
|
||
| #include <functional> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
it seems useless.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
removed
| /*num_experts=*/model_args.n_routed_experts(), | ||
| /*top_k=*/model_args.num_experts_per_tok(), | ||
| /*num_expert_group=*/model_args.n_group(), | ||
| /*topk_group=*/model_args.topk_group(), |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
no need to add such comments for these var.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
all clean now!
xllm/core/layers/common/dense_mlp.h
Outdated
| bool is_gated, | ||
| bool has_bias, | ||
| const std::string& hidden_act, | ||
| bool if_reduce_results, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: use bool enable_result_reduction.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
fixed
xllm/models/llm/mlu/deepseek_v2.h
Outdated
| ==============================================================================*/ | ||
| #pragma once | ||
|
|
||
| #include <gflags/gflags.h> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
seems useless
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
removed
d83692b to
b2f779c
Compare
No description provided.