spec : add DFlash2 support (local convolution + candidate selector) (#27342) (#27816)

* spec : add DFlash2 support (local convolution + candidate selector) (#27342) * support DFlash2 * Add p_min in DFlash2 Assisted-by: Claude Opus 5 * Revert unnecessary changes Assisted-by: Claude Opus 5 * Revert draft sampling in rejection sampling Assisted-by: Claude Opus 5 * Refactor code structure Assisted-by: Claude Opus 5 * Delete embedding scaling Assisted-by: Claude Opus 5 * Gate output transforms on DFlash2 Assisted-by: Claude Opus 5 * Optimize Dflash 2 cost Assisted-by: Claude Opus 5 * Avoid using atoi Assisted-by: Claude Opus 5 * Modify comments Assisted-by: Claude Opus 5 * Move llama_model_dflash_selector_top_k to llama-ext.h Assisted-by: Claude Opus 5 * Formatting Assisted-by: Claude Opus 5 * Apply patch to fix the mrope bug Assisted-by: Claude Opus 5 * fix ci Assisted-by: Claude Opus 5 * Fix graph number calculation Assisted-by: Claude Opus 5 * rename hid and unary Assisted-by: Claude Opus 5 --------- Co-authored-by: Jian Chen <jianchen0311@gmail.com> Co-authored-by: Xuan-Son Nguyen <son@huggingface.co> * revert top-k.cu changes --------- Co-authored-by: Zihan Zhang <tiancaizhangdaxian@sjtu.edu.cn> Co-authored-by: Jian Chen <jianchen0311@gmail.com>
2026-08-27 19:17:07 +02:00
parent 58546250cf
commit b10f9ca58c
15 changed files with 538 additions and 24 deletions
@@ -387,6 +387,11 @@ enum llm_kv {

    LLM_KV_TARGET_LAYERS,
    LLM_KV_TARGET_HIDDEN_SIZE,
+    LLM_KV_DFLASH_BLOCK_SIZE,
+    LLM_KV_DFLASH_CONV_KERNEL_SIZE,
+    LLM_KV_DFLASH_CONV_GROUP_SIZE,
+    LLM_KV_DFLASH_SELECTOR_RANK,
+    LLM_KV_DFLASH_SELECTOR_TOP_K,
    LLM_KV_NORM_BEFORE_RESIDUAL,
    LLM_KV_NORM_BEFORE_FC,

@@ -659,6 +664,13 @@ enum llm_tensor {
    LLM_TENSOR_DSPARK_MARKOV_W1,
    LLM_TENSOR_DSPARK_MARKOV_W2,
    LLM_TENSOR_DSPARK_CONF_PROJ,
+    LLM_TENSOR_DFLASH_ATTN_CONV_BASE,
+    LLM_TENSOR_DFLASH_ATTN_CONV_PROJ,
+    LLM_TENSOR_DFLASH_FFN_CONV_BASE,
+    LLM_TENSOR_DFLASH_FFN_CONV_PROJ,
+    LLM_TENSOR_DFLASH_SELECTOR_PREV,
+    LLM_TENSOR_DFLASH_SELECTOR_NEXT,
+    LLM_TENSOR_DFLASH_SELECTOR_HIDDEN,
 };