From 1fed1bc0518d492ea9c94ddd7486dd039fa758f8 Mon Sep 17 00:00:00 2001 From: Claude Date: Sat, 8 Aug 2026 10:57:02 +0000 Subject: [PATCH] fix: add --max-seq-len-to-capture 32768, fix patch_ops.sh contradictory comments Both base engine yaml and Sub168 use max-seq-len-to-capture=32768. We were missing it. Also fixed patch_ops.sh ending comments that claimed files were NOT deployed when they actually ARE deployed. --- computility-run.yaml | 2 ++ qwen3_6_scripts/patch_ops.sh | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/computility-run.yaml b/computility-run.yaml index 02adf99e..e17f30ff 100644 --- a/computility-run.yaml +++ b/computility-run.yaml @@ -28,6 +28,8 @@ command: - qwen3 - --enable-prefix-caching - --enable-chunked-prefill + - --max-seq-len-to-capture + - '32768' - --dtype - half env: diff --git a/qwen3_6_scripts/patch_ops.sh b/qwen3_6_scripts/patch_ops.sh index 58b395fe..8583a9ca 100755 --- a/qwen3_6_scripts/patch_ops.sh +++ b/qwen3_6_scripts/patch_ops.sh @@ -177,6 +177,6 @@ if [ -n "$VLLM2" ]; then cp ./chat_utils.py "$VLLM2/entrypoints/chat_utils.py" 2>/dev/null || true fi -echo "[patch_ops] DONE — serving layer + qwen3_5.py model module deployed" -echo "[patch_ops] Deployed: qwen3_5.py (model module, required for registry import)" -echo "[patch_ops] NOT deployed (base image native): model_runner.py, _custom_ops.py, sampler.py, scheduler.py, sequence.py, xformers.py, paged_attn.py, prefix_prefill.py, logits_processor.py, mamba_cache.py, arg_utils.py" +echo "[patch_ops] DONE — full base engine patches + serving layer deployed" +echo "[patch_ops] Deployed: qwen3_5.py, paged_attn.py, mamba_cache.py, sequence.py, scheduler.py, xformers patches, serving layer" +echo "[patch_ops] NOT deployed (base image native): model_runner.py, _custom_ops.py, sampler.py, logits_processor.py, arg_utils.py"