This repository has been archived by the owner on Oct 11, 2024. It is now read-only.
Upstream sync 2024 06 08 #288
Merged
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
Co-authored-by: Alexey Kondratiev <[email protected]>
Allow dummy load format for fp8, torch.uniform_ doesn't support FP8 at the moment Co-authored-by: Mor Zusman <[email protected]>
Signed-off-by: kerthcet <[email protected]>
Pass the CUDA stream into the CUTLASS GEMMs, to avoid future issues with CUDA graphs
…ct#4893) The 2nd PR for vllm-project#4532. This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).
Signed-off-by: Muralidhar Andoorveedu <[email protected]>
Co-authored-by: Varun Sundar Rabindranath <[email protected]> Co-authored-by: Varun Sundar Rabindranath <[email protected]>
…project#4985) Co-authored-by: Elisei Smirnov <[email protected]>
robertgshaw2-redhat
added a commit
that referenced
this pull request
Jun 11, 2024
Upstream sync 2024 06 11 (#288) SUMMARY: * Merge commits from vllm-project@1197e02 to vllm-project@114332b * Our GCP test instances do not have gcc or clang installed. All of the triton kernels rely on the gcc and clang to generate JITs. These are still disabled (cc @andy-neuma). All are marked with: ```python @pytest.mark.skip("C compiler not installed in NM automation. " "This codepath follows a triton pathway, which " "JITs using clang or gcc. Since neither are installed " "in our test instances, we need to skip this for now.") ``` Note that vllm-project@1197e02 is NOT included in this merge. COMPARE vs UPSTREAM: https://github.com/neuralmagic/nm-vllm/compare/upstream-sync-2024-06-11..vllm-project:vllm:v0.5.0 --------- Signed-off-by: Ye Cao <[email protected]> Signed-off-by: kevin <[email protected]> Co-authored-by: Daniele <[email protected]> Co-authored-by: Tyler Michael Smith <[email protected]> Co-authored-by: Varun Sundar Rabindranath <[email protected]> Co-authored-by: Varun Sundar Rabindranath <[email protected]> Co-authored-by: Ye Cao <[email protected]> Co-authored-by: Nadav Shmayovits <[email protected]> Co-authored-by: chenqianfzh <[email protected]> Co-authored-by: Zhuohan Li <[email protected]> Co-authored-by: Daniil Arapov <[email protected]> Co-authored-by: mgoin <[email protected]> Co-authored-by: Simon Mo <[email protected]> Co-authored-by: Avinash Raj <[email protected]> Co-authored-by: Divakar Verma <[email protected]> Co-authored-by: Cyrus Leung <[email protected]> Co-authored-by: Antoni Baum <[email protected]> Co-authored-by: Yuan <[email protected]> Co-authored-by: Kaiyang Chen <[email protected]> Co-authored-by: Kevin H. Luu <[email protected]> Co-authored-by: Breno Faria <[email protected]> Co-authored-by: Toshiki Kataoka <[email protected]> Co-authored-by: Woosuk Kwon <[email protected]> Co-authored-by: afeldman-nm <[email protected]> Co-authored-by: zifeitong <[email protected]> Co-authored-by: Jie Fu (傅杰) <[email protected]> Co-authored-by: Li, Jiang <[email protected]> Co-authored-by: youkaichao <[email protected]> Co-authored-by: tomeras91 <[email protected]> Co-authored-by: Cody Yu <[email protected]> Co-authored-by: DriverSong <[email protected]> Co-authored-by: qiujiawei9 <[email protected]> Co-authored-by: Philipp Moritz <[email protected]> Co-authored-by: Nick Hill <[email protected]> Co-authored-by: Alex Wu <[email protected]> Co-authored-by: Breno Faria <[email protected]> Co-authored-by: liuyhwangyh <[email protected]> Co-authored-by: mulin.lyh <[email protected]> Co-authored-by: Matthew Goldey <[email protected]> Co-authored-by: Jie Fu (傅杰) <[email protected]> Co-authored-by: Itay Etelis <[email protected]> Co-authored-by: limingshu <[email protected]> Co-authored-by: Dipika Sikka <[email protected]> Co-authored-by: Roger Wang <[email protected]> Co-authored-by: Calvinn Ng <[email protected]> Co-authored-by: team <[email protected]> Co-authored-by: Cheng Li <[email protected]> Co-authored-by: Benjamin Kitor <[email protected]> Co-authored-by: Hongxia Yang <[email protected]> Co-authored-by: bnellnm <[email protected]> Co-authored-by: Bla_ckB <[email protected]> Co-authored-by: Roger Wang <[email protected]>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Upstream sync 2024 06 08 (#288) - ties to v0.4.3 of vllm-upstream
SUMMARY:
gccorclanginstalled. All of the triton kernels rely on thegccandclangto generate JITs. I disabled these for now, but we need to get these installed (cc @andy-neuma). All are marked with:Note that vllm-project@f68470e is NOT included in this merge.
COMPARE vs UPSTREAM: