Merged
Conversation
…it (>= 0.15).
Unfortunately, it currently fails with VLLM 0.15.1 in our env:
File ".../vllm/v1/worker/gpu_worker.py", line 412, in initialize_from_config
self.model_runner.initialize_kv_cache(kv_cache_config)
File ".../vllm/v1/worker/gpu_model_runner.py", line 5874, in initialize_kv_cache
self.initialize_attn_backend(kv_cache_config)
File ".../vllm/v1/worker/gpu_model_runner.py", line 5225, in initialize_attn_backend
check_attention_cp_compatibility(self.vllm_config)
File ".../vllm/v1/worker/cp_utils.py", line 39, in check_attention_cp_compatibility
assert layer_impl.supports_pcp, (
AssertionError: PCP requires attention impls' support, but the impl FlashAttentionImpl does not support PCP.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Also start to implement context parallelism (when the version of VLLM permits it), but unfortunately that is still failing in our env with VLLM 0.15.1 :