Skip to content

llama : enforce the same K and V cache types for DeepSeek V4; enable FA if V cache is quantized #25871

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
fairydreaming wants to merge 1 commit into
base: master
Choose a base branch
from
+16 −5
Open

llama : enforce the same K and V cache types for DeepSeek V4; enable FA if V cache is quantized #25871

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 16 additions & 5 deletions src/llama-context.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3538,6 +3538,22 @@ llama_context * llama_init_from_model(
}
}

if (model->arch == LLM_ARCH_DEEPSEEK4 && params.type_k != params.type_v) {

@fairydreaming fairydreaming Jul 18, 2026

Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this currently applies also to DeepSeek V3.2 and models where hparams.is_mla() is true since they use a view of K cache as V cache, maybe it's worth extending the condition?

@ggerganov ggerganov Jul 27, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, sounds good

LLAMA_LOG_ERROR("%s: DeepSeek V4 does not support different K (%s) and V (%s) cache types\n", __func__, ggml_type_name(params.type_k), ggml_type_name(params.type_v));
return nullptr;
}

if (ggml_is_quantized(params.type_v) && params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_ENABLED) {
if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_AUTO) {
LLAMA_LOG_INFO("%s: enabling flash_attn since it is required for quantized V cache\n", __func__);
params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_ENABLED;
}
if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_DISABLED) {
LLAMA_LOG_ERROR("%s: quantized V cache requires flash_attn to be enabled\n", __func__);
return nullptr;
}
}

if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_k)) {
const uint32_t blck_size = ggml_blck_size(params.type_k);
for (uint32_t il = 0; il < model->hparams.n_layer(); ++il) {
Expand All @@ -3560,11 +3576,6 @@ llama_context * llama_init_from_model(
}
}

if (ggml_is_quantized(params.type_v) && params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_DISABLED) {
LLAMA_LOG_ERROR("%s: V cache quantization requires flash_attn\n", __func__);
return nullptr;
}

if (params.pooling_type != LLAMA_POOLING_TYPE_UNSPECIFIED &&
params.pooling_type != model->hparams.pooling_type) {
//user-specified pooling-type is different from the model default
Expand Down
Loading