vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'ggerganov:master' into master

Browse source
This commit is contained in:
Ziang Wu 2024-03-28 21:41:19 +08:00 • committed by GitHub
commit 1ef3250abd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

3
.github/workflows/bench.yml vendored
View file

@ -42,7 +42,7 @@ jobs:
RUNNER_LABEL: Standard_NC4as_T4_v3 # FIXME Do not find a way to not duplicate it
N_USERS: 8
DURATION: 10m
if: ${{ github.event.inputs.gpu-series == 'Standard_NC4as_T4_v3' || github.event.schedule || github.event.pull_request || github.event.push.ref == 'refs/heads/master' }}
if: ${{ github.event.inputs.gpu-series == 'Standard_NC4as_T4_v3' || github.event.schedule || github.event.pull_request || github.head_ref == 'master' || github.ref_name == 'master' || github.event.push.ref == 'refs/heads/master' }}
steps:
- name: Clone
id: checkout
@ -143,6 +143,7 @@ jobs:
- name: Commit status
uses: Sibz/github-status-action@v1
continue-on-error: true # If not authorized on external repo
with:
authToken: ${{secrets.GITHUB_TOKEN}}
sha: ${{ inputs.sha || github.event.pull_request.head.sha || github.sha }}

5
llama.cpp
View file

@ -9152,8 +9152,9 @@ struct llm_build_context {
if (il == n_layer - 1) {
// skip computing output for unused tokens
struct ggml_tensor * inp_out_ids = build_inp_out_ids();
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
cur = ggml_get_rows(ctx0, cur, inp_out_ids);
inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);
ffn_inp = ggml_get_rows(ctx0, ffn_inp, inp_out_ids);
}
struct ggml_tensor * attn_out = cur;