Skip to content

fix: session_tokens insert range in completion tool (no-op → correct)#20917

Merged
danbev merged 1 commit into
ggml-org:masterfrom
mtmcp:completion-fix-session-range
Mar 27, 2026
Merged

fix: session_tokens insert range in completion tool (no-op → correct)#20917
danbev merged 1 commit into
ggml-org:masterfrom
mtmcp:completion-fix-session-range

Conversation

@mtmcp

@mtmcp mtmcp commented Mar 23, 2026

Copy link
Copy Markdown
Collaborator

Overview

The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
decoding. Should be embd.begin(), embd.end(). Introduced in commit 2b6dfe8.

Requirements

  The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
  decoding. Should be embd.begin(), embd.end(). Introduced in commit 2b6dfe8.
@mtmcp mtmcp requested a review from ggerganov as a code owner March 23, 2026 20:58
@mtmcp mtmcp requested review from danbev and removed request for ggerganov March 23, 2026 20:58
@ggml-gh-bot

This comment was marked as resolved.

@danbev danbev merged commit 37f230d into ggml-org:master Mar 27, 2026
48 checks passed
slartibardfast pushed a commit to slartibardfast/llama.cpp that referenced this pull request Apr 12, 2026
…correct) (ggml-org#20917)

The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
  decoding. Should be embd.begin(), embd.end(). Introduced in commit 2b6dfe8.
Seunghhon pushed a commit to Seunghhon/llama.cpp that referenced this pull request Apr 26, 2026
…correct) (ggml-org#20917)

The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
  decoding. Should be embd.begin(), embd.end(). Introduced in commit 2b6dfe8.
ljubomirj pushed a commit to ljubomirj/llama.cpp that referenced this pull request May 6, 2026
…correct) (ggml-org#20917)

The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
  decoding. Should be embd.begin(), embd.end(). Introduced in commit 4f4d17a.
my-other-github-account pushed a commit to my-other-github-account/llama.cpp that referenced this pull request May 15, 2026
…correct) (ggml-org#20917)

The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
  decoding. Should be embd.begin(), embd.end(). Introduced in commit 6c2789c.
my-other-github-account pushed a commit to my-other-github-account/llama.cpp that referenced this pull request May 15, 2026
…correct) (ggml-org#20917)

The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
  decoding. Should be embd.begin(), embd.end(). Introduced in commit ef66a16.
fewtarius pushed a commit to fewtarius/CachyLLama that referenced this pull request May 30, 2026
…correct) (ggml-org#20917)

The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
  decoding. Should be embd.begin(), embd.end(). Introduced in commit bc3fbff.
fukuro-kun pushed a commit to fukuro-kun/fukuro-llama-cpp-turboquant that referenced this pull request Jul 5, 2026
…correct) (ggml-org#20917)

The embd.begin(), embd.begin() range is empty and inserts nothing, so session_tokens never gets updated after
  decoding. Should be embd.begin(), embd.end(). Introduced in commit 67a20b7.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants