Enabed test cases for disaggregate_prefill_v1 with lmcache on hpu, gaudi-nic, cpuoverloading. #1370
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
…udi-nic, cpuoverloading.
…che, fix prefill and add lm for pd (#1352) Co-authored-by: Yeonsil Yoon <yeon.sil.yoon@intel.com>
hsubramony
requested review from
kzawora-intel,
madamczyk-intel,
michalkuligowski,
mgawarkiewicz-intel,
vivekgoe,
afierka-intel,
xuechendi,
jikunshang and
mswiniarsk
as code owners
michalkuligowski
requested changes
Jun 5, 2025
| @@ -0,0 +1,100 @@ | |||
| # SPDX-License-Identifier: Apache-2.0 | |||
There was a problem hiding this comment.
Please provide description of the PR including why we need those examples on CPU
| @@ -0,0 +1,74 @@ | |||
| INFO 05-05 16:12:54 [__init__.py:248] Automatically detected platform hpu. | |||
Comment on lines
+41
to
+46
| #GAUDI-NIC | ||
| #os.environ["LMCACHE_NIXL_BUFFER_SIZE"] = "1073741824" | ||
| #os.environ["LMCACHE_NIXL_RECEIVER_HOST"] = "localhost" | ||
| #os.environ["LMCACHE_NIXL_RECEIVER_PORT"] = "66666" | ||
| #os.environ["LMCACHE_NIXL_BUFFER_DEVICE"] = "hpu" | ||
| #os.environ["LMCACHE_NIXL_ENABLE_GC"] = "True" |
| decoder_rank = '1' | ||
| os.environ["RANK"] = decoder_rank | ||
| os.environ["LMCACHE_NIXL_ROLE"] = "RECEIVER" | ||
| #sampling_params = SamplingParams(temperature=0, top_p=0.95, max_tokens=10) |
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Outdated suggestions cannot be applied.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.
No description provided.