Disaggregate prefill for kv cache register style (#950)
### What this PR does / why we need it?
This PR adopt `LLMDataDist` for kv cache register and `pull_blocks`
style disaggregate prefill implementation. The interface implementation
mainly follows the design of NIXL PR
https://github.com/vllm-project/vllm/pull/17751/files#diff-7eaad0b7dee0626bf29d10081b0f0c5e3ea15a4af97e7b182a4e0d35f8346953
.
This PR can be test with the following step:
- Generate the rank table for all machine.
- execute`toy_proxy.py` to launch the disaggregate prefill proxy server,
specify the prefill ip, port and the decode ip, port
- Run the prefill server and decode server.
- send the request to the disaggregate prefill proxy
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.9.2
- vLLM main:
8d0a01a5f2
---------
Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
Signed-off-by: machenglong <machenglong_yewu@cmss.chinamobile.com>
Signed-off-by: liziyu179 <3475441767@qq.com>
Signed-off-by: underfitc <hucong24@huawei.com>
Signed-off-by: zouyida2052 <zouyida@huawei.com>
Signed-off-by: liziyu <liziyu16@huawei.com>
Signed-off-by: underfituu <hzhucong@163.com>
Co-authored-by: machenglong <machenglong_yewu@cmss.chinamobile.com>
Co-authored-by: liziyu179 <3475441767@qq.com>
Co-authored-by: underfitc <hucong24@huawei.com>
Co-authored-by: zouyida2052 <zouyida@huawei.com>
Co-authored-by: liziyu <liziyu16@huawei.com>
Co-authored-by: underfituu <hzhucong@163.com>
This commit is contained in:
7
.github/workflows/vllm_ascend_test_pd.yaml
vendored
7
.github/workflows/vllm_ascend_test_pd.yaml
vendored
@@ -42,8 +42,7 @@ jobs:
|
||||
strategy:
|
||||
matrix:
|
||||
vllm_verison: [
|
||||
# revert me when V1 disaggregation prefill is merged in main
|
||||
# main,
|
||||
main,
|
||||
v0.9.1
|
||||
]
|
||||
name: vLLM Ascend prefilling decoding disaggregation test
|
||||
@@ -107,6 +106,6 @@ jobs:
|
||||
pip install -r requirements-dev.txt
|
||||
pip install -v -e .
|
||||
|
||||
- name: Run vllm-project/vllm-ascend PD Disaggregation test
|
||||
- name: Run vllm-project/vllm-ascend PD Disaggregation edge test
|
||||
run: |
|
||||
pytest -sv tests/e2e/pd_disaggreate/test_pd_e2e.py
|
||||
bash tests/e2e/pd_disaggreate/run_edge_case_test.sh
|
||||
Reference in New Issue
Block a user