Skip to content

feat(llama.cu): 适配 mamba 模型 #48

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.

Sign up for GitHub

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

Open
CearX wants to merge 2 commits into
base: llama.cu
Choose a base branch
from

feat(llama.cu): 添加 mamba engine，支持测试 ppl

dcdde0a
Select commit
Loading
Failed to load commit list.
Open

feat(llama.cu): 适配 mamba 模型 #48

feat(llama.cu): 添加 mamba engine，支持测试 ppl
dcdde0a
Select commit
Loading
Failed to load commit list.
GitHub Advanced Security / clippy succeeded Aug 24, 2025 in 3s

24 new alerts

New alerts in code changed by this pull request

  • 24 warnings

See annotations below for details.

View all branch alerts.

Annotations

Check warning on line 108 in llama.cu/src/exec/mamba_engine.rs

See this annotation in the file changed.

Code scanning / clippy

the loop variable i is used to index host_logits_f16 Warning

the loop variable i is used to index host_logits_f16

Check warning on line 108 in llama.cu/src/exec/mamba_engine.rs

See this annotation in the file changed.

Code scanning / clippy

the loop variable i is used to index host_logits_f16 Warning

the loop variable i is used to index host_logits_f16

Check warning on line 126 in llama.cu/src/exec/mamba_engine.rs

See this annotation in the file changed.

Code scanning / clippy

the loop variable i is used to index host_logits_f32 Warning

the loop variable i is used to index host_logits_f32

Check warning on line 126 in llama.cu/src/exec/mamba_engine.rs

See this annotation in the file changed.

Code scanning / clippy

the loop variable i is used to index host_logits_f32 Warning

the loop variable i is used to index host_logits_f32

Check warning on line 364 in llama.cu/src/exec/mamba_engine.rs

See this annotation in the file changed.

Code scanning / clippy

this function has too many arguments (8/7) Warning

this function has too many arguments (8/7)

Check warning on line 364 in llama.cu/src/exec/mamba_engine.rs

See this annotation in the file changed.

Code scanning / clippy

this function has too many arguments (8/7) Warning

this function has too many arguments (8/7)

Check warning on line 419 in llama.cu/src/exec/mamba_engine.rs

See this annotation in the file changed.

Code scanning / clippy

this function has too many arguments (8/7) Warning

this function has too many arguments (8/7)

Check warning on line 419 in llama.cu/src/exec/mamba_engine.rs

See this annotation in the file changed.

Code scanning / clippy

this function has too many arguments (8/7) Warning

this function has too many arguments (8/7)

Check warning on line 12 in llama.cu/src/lib.rs

See this annotation in the file changed.

Code scanning / clippy

unused import: GGufMetaMap Warning

unused import: GGufMetaMap

Check warning on line 12 in llama.cu/src/lib.rs

See this annotation in the file changed.

Code scanning / clippy

unused import: GGufMetaMap Warning

unused import: GGufMetaMap

Check warning on line 11 in xtask/src/service/error.rs

See this annotation in the file changed.

Code scanning / clippy

variant name ends with the enum's name Warning

variant name ends with the enum's name

Check warning on line 11 in xtask/src/service/error.rs

See this annotation in the file changed.

Code scanning / clippy

variant name ends with the enum's name Warning

variant name ends with the enum's name

Check warning on line 471 in xtask/src/service/mod.rs

See this annotation in the file changed.

Code scanning / clippy

unused variable: no_cuda_graph Warning

unused variable: no_cuda_graph

Check warning on line 471 in xtask/src/service/mod.rs

See this annotation in the file changed.

Code scanning / clippy

unused variable: no_cuda_graph Warning

unused variable: no_cuda_graph

Check warning on line 121 in xtask/src/service/model.rs

See this annotation in the file changed.

Code scanning / clippy

unused variable: use_cuda_graph Warning

unused variable: use_cuda_graph

Check warning on line 121 in xtask/src/service/model.rs

See this annotation in the file changed.

Code scanning / clippy

unused variable: use_cuda_graph Warning

unused variable: use_cuda_graph

Check warning on line 495 in xtask/src/service/model.rs

See this annotation in the file changed.

Code scanning / clippy

methods compute_logprobs and compute_sequence_logprobs are never used Warning

methods compute_logprobs and compute_sequence_logprobs are never used

Check warning on line 495 in xtask/src/service/model.rs

See this annotation in the file changed.

Code scanning / clippy

methods compute_logprobs and compute_sequence_logprobs are never used Warning

methods compute_logprobs and compute_sequence_logprobs are never used

Check warning on line 506 in xtask/src/service/model.rs

See this annotation in the file changed.

Code scanning / clippy

value assigned to token_logprobs is never read Warning

value assigned to token_logprobs is never read

Check warning on line 506 in xtask/src/service/model.rs

See this annotation in the file changed.

Code scanning / clippy

value assigned to token_logprobs is never read Warning

value assigned to token_logprobs is never read

Check warning on line 527 in xtask/src/service/model.rs

See this annotation in the file changed.

Code scanning / clippy

methods compute_logprobs and compute_sequence_logprobs are never used Warning

methods compute_logprobs and compute_sequence_logprobs are never used

Check warning on line 527 in xtask/src/service/model.rs

See this annotation in the file changed.

Code scanning / clippy

methods compute_logprobs and compute_sequence_logprobs are never used Warning

methods compute_logprobs and compute_sequence_logprobs are never used

Check warning on line 121 in xtask/src/service/openai.rs

See this annotation in the file changed.

Code scanning / clippy

this function has too many arguments (8/7) Warning

this function has too many arguments (8/7)

Check warning on line 121 in xtask/src/service/openai.rs

See this annotation in the file changed.

Code scanning / clippy

this function has too many arguments (8/7) Warning

this function has too many arguments (8/7)