[Bugfix] Sparse MLA: enable fp8_ds_mla dense prefill (#48642)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com> Co-authored-by: OpenAI Codex <noreply@openai.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
OpenAI Codex
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
f17be06fbe
commit
67f9046e4a
+1
-2
@@ -67,9 +67,8 @@ void cp_gather_and_upconvert_fp8_kv_cache(
|
||||
torch::Tensor const& src_cache, // [NUM_BLOCKS, BLOCK_SIZE, 656]
|
||||
torch::Tensor const& dst, // [TOT_TOKENS, 576]
|
||||
torch::Tensor const& block_table, // [BATCH, BLOCK_INDICES]
|
||||
torch::Tensor const& seq_lens, // [BATCH]
|
||||
torch::Tensor const& workspace_starts, // [BATCH]
|
||||
int64_t batch_size);
|
||||
int64_t batch_size, std::optional<torch::Tensor> seq_starts = std::nullopt);
|
||||
|
||||
// Indexer K quantization and cache function
|
||||
void indexer_k_quant_and_cache(
|
||||
|
||||
Reference in New Issue
Block a user