Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

DeepseekV4: fix rollback with multi-seq (#26756)

Browse Source 
* DeepseekV4: fix rollback with multi-seq

* fix model loading

* make pending rollback single use

* only clear cache for seq_id for full load

* add assert for compress ratio

* make graph topology static

* pass true instead of flags in clear_compressed

* cont : clean-up + TODOs

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Aman Gupta
2026-08-23 13:57:49 +03:00
committed by GitHub
co-authored by Georgi Gerganov
parent d3371929bb
commit b0539c43ed
10 changed files with 345 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama.h
+1 -1
View File
@@ -733,7 +733,7 @@ extern "C" {
// Removes all tokens that belong to the specified sequence and have positions in [p0, p1)
// Returns false if a partial sequence cannot be removed. Removing a whole sequence never fails
// seq_id < 0 : match any sequence
// seq_id < 0 : match any sequence [TAG_LLAMA_SEQ_ID_NEG]
// p0 < 0 : [0, p1]
// p1 < 0 : [p0, inf)
LLAMA_API bool llama_memory_seq_rm(