[fix] baseline5 1.8192->4096 solve oom 2. bridge.linear 导过去

2026-08-20 06:33:38 +00:00
parent 882669b0bc
commit 8842a5ffef
4 changed files with 569 additions and 2 deletions
--- a/computility-run.yaml
+++ b/computility-run.yaml
@@ -10,7 +10,7 @@ command:
    - --max-model-len
    - '131072'
    - --gpu-memory-utilization
-    - '0.90'
+    - '0.95'
    - --trust-remote-code
    - -tp
    - '4'
@@ -19,7 +19,7 @@ command:
    - --disable-log-requests
    - --disable-frontend-multiprocessing
    - --max-num-batched-tokens
-    - '8192'
+    - '4096'
    - --enable-chunked-prefill
    - --max-seq-len-to-capture
    - '32768'