[v0.9.1][Bugfix][PD] Auto-clear producer KV cache if no pull notification #2085
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: underfituu <[email protected]>
|
When is this feature needed? |
underfituu
force-pushed
the
fix_pd_expiry
branch
from
a30de4e to
f04bfbc
Compare
Signed-off-by: underfituu <[email protected]>
underfituu
force-pushed
the
fix_pd_expiry
branch
from
f04bfbc to
4e280dd
Compare
Signed-off-by: underfituu <[email protected]>
Signed-off-by: underfituu <[email protected]>
Signed-off-by: underfituu <[email protected]>
Signed-off-by: underfituu <[email protected]>
Signed-off-by: underfituu <[email protected]>
Signed-off-by: underfituu <[email protected]>
Trigger Scenarios:
Root Cause Analysis:
Solution:
Note: The full disaster recovery solution is still in design. This PR will be merged into v091-dev branch simply but will evolve in main (PR #2174).
|
ganyi1996ppo
approved these changes
Aug 5, 2025
liyu119
added a commit
to rjg-lyh/vllm-ascend
that referenced
this pull request
Aug 11, 2025
…nto qwen30-dev * 'qwen30-dev' of https://github.com/rjg-lyh/vllm-ascend: [V0.9.1] Replace FA ops with FA_V2 to optimize perf [0.9.1]remove chunked_prefill_for_mla (vllm-project#2177) move with_prefill allreduce from cpu to npu (vllm-project#2230) [v0.9.1] Add release note for v0.9.1rc2 (vllm-project#2233) [Docs] Sync main doc to v0.9.1-dev (vllm-project#2227) [0.9.1] Enable external distributed dp deployments in vllm ascend(0.9.1 only) (vllm-project#2109) [V0.9.1][BugFix] Fix the bug in decoraotor patch (vllm-project#2199) [v0.9.1][Bugfix][PD] Auto-clear producer KV cache if no pull notification (vllm-project#2085) [BUGFIX][0.9.1] FIX ring_mla input ‘query_lens’ to cpu (vllm-project#2170) [0.9.1][Prefill Perf] add D2H & initRoutingQuantV2 (vllm-project#2038) [bugfix] add with_prefill cpu allreduce to handle D-node recomputatio… (vllm-project#2129)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it?
This PR addresses a critical issue where Node D (Device) failures cause Node P (Processor) to hang due to inability to release KV cache.
Trigger Scenarios:
Root Cause Analysis:
Solution:
Following VLLM community's approach (NIXL connector timeout mechanism), we're implementing:
Note: The full disaster recovery solution is still in design. This PR will be merged into v091-dev branch simply but will evolve in main (PR #2174).
Does this PR introduce any user-facing change?
How was this patch tested?