[Perf] Fix TRTLLM ragged prefill perf regression (#55499)

Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Wei Zhao
2026-09-09 20:38:20 +00:00
committed by GitHub
co-authored by OpenAI Codex
parent 56d001faf0
commit 8c87c333b8
6 changed files with 51 additions and 4 deletions
+1 -1
View File
@@ -960,7 +960,7 @@ RUN --mount=type=cache,target=/opt/uv/cache \
# Install FlashInfer JIT cache (requires CUDA-version-specific index URL)
# https://docs.flashinfer.ai/installation.html
# From versions.json: .flashinfer.version
ARG FLASHINFER_VERSION=0.6.18
ARG FLASHINFER_VERSION=0.6.18.post1
RUN --mount=type=cache,target=/opt/uv/cache \
if [ "${INSTALL_RUBIN_PRERELEASE}" != "true" ]; then \
uv pip install --system flashinfer-jit-cache==${FLASHINFER_VERSION} \
+1 -1
View File
@@ -71,7 +71,7 @@
"default": "true"
},
"FLASHINFER_VERSION": {
"default": "0.6.18"
"default": "0.6.18.post1"
},
"GDRCOPY_CUDA_VERSION": {
"default": "12.8"