mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-21 14:26:30 +00:00
b95693056c
* feat: Bump llama.cpp to the latest master (17f7f4b) This brings in significant improvements to prefill performance for all models using the SSM_CONV and SSM_SCAN ops (granite4, jamba, falcon-h, nemotron-h, Qwen3 Next) on Apple Metal. See https://github.com/ggml-org/llama.cpp/pull/17876 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 1-4 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Update patches 5-12 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 13-18 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patch 20 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 21-31 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Sync vendored code The two files I'm not sure about here are the swap from gemma3-iswa.cpp to gemma3.cpp (I chose to include this because I think it's required), and the inclusion of `ggml-zendnn.h` which I chose to omit. Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
24 lines
948 B
Diff
24 lines
948 B
Diff
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
|
|
From: Michael Yang <git@mxy.ng>
|
|
Date: Mon, 18 Aug 2025 16:58:39 -0700
|
|
Subject: [PATCH] decode: disable output_all
|
|
|
|
---
|
|
src/llama-context.cpp | 3 +--
|
|
1 file changed, 1 insertion(+), 2 deletions(-)
|
|
|
|
diff --git a/src/llama-context.cpp b/src/llama-context.cpp
|
|
index 417140071..87f407f99 100644
|
|
--- a/src/llama-context.cpp
|
|
+++ b/src/llama-context.cpp
|
|
@@ -999,8 +999,7 @@ int llama_context::decode(const llama_batch & batch_inp) {
|
|
const int64_t n_vocab = vocab.n_tokens();
|
|
const int64_t n_embd = hparams.n_embd_inp();
|
|
|
|
- // when computing embeddings, all tokens are output
|
|
- const bool output_all = cparams.embeddings;
|
|
+ const bool output_all = false;
|
|
|
|
if (!balloc->init(batch_inp, vocab, memory.get(), n_embd, cparams.kv_unified ? LLAMA_MAX_SEQ : cparams.n_seq_max, output_all)) {
|
|
LLAMA_LOG_ERROR("%s: failed to initialize batch\n", __func__);
|