[DeepseekR1] running with multi nodes #819
Closed
Conversation
This file contains 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: Chendi Xue <chendi.xue@intel.com>
topk_group not support issue Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
1. move block_fp8 pad to load_weight 2. move moe fp8 linear out of loop 3. remove permute and reshape --------- Signed-off-by: Chendi Xue <chendi.xue@intel.com> Co-authored-by: root <root@g3lc-srv32-c03d-idc.idc9.habana-labs.com>
Add VLLM_MOE_N_SLICE in test script and fix warmup bucket Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com> Signed-off-by: simon-mo <xmo@berkeley.edu> Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Co-authored-by: simon-mo <simon.mo@hey.com> Co-authored-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Zhuohan Li <zhuohan123@gmail.com> Co-authored-by: Tyler Michael Smith <tysmith@redhat.com> Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com> Co-authored-by: simon-mo <xmo@berkeley.edu>
) This PR implements the Deepseek V3 support by performing matrix absorption the fp8 weights --------- Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com> Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Co-authored-by: simon-mo <simon.mo@hey.com> Co-authored-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Zhuohan Li <zhuohan123@gmail.com> Co-authored-by: Tyler Michael Smith <tysmith@redhat.com> Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com>
FILL IN THE PR DESCRIPTION HERE FIX #xxxx (*link existing issues this PR will resolve*) **BEFORE SUBMITTING, PLEASE READ https://docs.vllm.ai/en/latest/contributing/overview.html ** Signed-off-by: Chendi Xue <chendi.xue@intel.com>
enable with env var VLLM_EP_SIZE=4 VLLM_MOE_N_SLICE=1 gpu_util=0.8 => for bs=96, otherwise it triggers OOM issue EP_size will be part of TP size. Ex: TP = 8, if we set EP==4, we will reduce TP in MOE as 2 --------- Signed-off-by: Chendi Xue <chendi.xue@intel.com>
HabanaAI#790) Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
…512 in value cache (HabanaAI#804) Before, we can only allocate 1854 blocks with 29.2G, now we are able to allocate 3156 blocks Performance wise, not visible regression and able to push to higher batch_size or longer context length --------- Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
xuechendi
requested review from
kzawora-intel,
madamczykhabana,
michalkuligowski,
mgawarkiewicz,
vivekgoe and
afierka-intel
as code owners
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.