[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:
Matthew Bonanni
2026-07-16 22:44:04 +00:00
committed by GitHub
co-authored by OpenAI Codex mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent f17be06fbe
commit 67f9046e4a
13 changed files with 516 additions and 85 deletions
+1 -2
View File
@@ -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(