biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[TPU] Add support for online w8a8 quantization (#22425)

Browse Source 
Signed-off-by: Kyuyeun Kim <kyuyeunk@google.com>
This commit is contained in:
Kyuyeun Kim
2025-08-08 23:12:54 -07:00
committed by GitHub
parent 10a02535d4
commit 9a0c5ded5a
3 changed files with 82 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/scripts/hardware_ci/run-tpu-v1-test-part2.sh
View File

@@ -139,6 +139,8 @@ run_and_track_test 5 "test_spmd_model_weight_loading.py" \
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_spmd_model_weight_loading.py"
run_and_track_test 6 "test_kv_cache_update_kernel.py" \
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_kv_cache_update_kernel.py"
run_and_track_test 7 "test_tpu_int8.py" \
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_tpu_int8.py"
# After all tests have been attempted, exit with the overall status.
if [ "$overall_script_exit_code" -ne 0 ]; then