Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[WIP] Test on oneAPI 2024.1.1 #22

Draft
wants to merge 228 commits into
base: use-sycl-backend
Choose a base branch
from
Draft

[WIP] Test on oneAPI 2024.1.1 #22

wants to merge 228 commits into from

Conversation

xiangyuT
Copy link
Collaborator

@xiangyuT xiangyuT commented Aug 6, 2024

No description provided.

WoosukKwon and others added 30 commits July 21, 2024 18:43
@WoosukKwon
[Misc] Add a wrapper for torch.inference_mode (vllm-project#6618)
42de2ce
@jaywonchung
[Bugfix] Fix vocab_size field access in llava_next.py (vllm-proje…
89c1c6a 
…ct#6624)
@DarkLight1337 @ywang96
[Frontend] Refactor prompt processing (vllm-project#4028)
739b61a 
Co-authored-by: Roger Wang <[email protected]>
@tlrmchlsmth
[Bugfix][Kernel] Use int64_t for indices in fp8 quant kernels (vllm-p…
fea59c7 
…roject#6649)
@khluu
[ci] Use different sccache bucket for CUDA 11.8 wheel build (vllm-pro…
69d5ae3 
…ject#6656)

Signed-off-by: kevin <[email protected]>
@Jeffwan @Yard1
[Core] Support dynamically loading Lora adapter from HuggingFace (vll…
42c7f66 
…m-project#6234)

Co-authored-by: Antoni Baum <[email protected]>
@youkaichao
[ci][build] add back vim in docker (vllm-project#6661)
5a96ee5
@WoosukKwon
[Misc] Remove deprecation warning for beam search (vllm-project#6659)
bdf5fd1
@comaniac
[Core] Modulize prepare input and attention metadata builder (vllm-pr…
e0c1575 
…oject#6596)
@cli99
[Bugfix] Fix null modules_to_not_convert in FBGEMM Fp8 quantization (…
c5e8330 
…vllm-project#6665)
@WoosukKwon
[Misc] Enable chunked prefill by default for long context models (vll…
729171a 
…m-project#6666)
@youkaichao
[misc] add start loading models for users information (vllm-project#6670
7c2749a 
)
@zhaotyer @youkaichao
add tqdm when loading checkpoint shards (vllm-project#6569)
e519ae0 
Co-authored-by: tianyi.zhao <[email protected]>
Co-authored-by: youkaichao <[email protected]>
@mgoin
[Misc] Support FP8 kv cache scales from compressed-tensors (vllm-proj…
9e0b558 
…ect#6528)
@youkaichao
[doc][distributed] doc for setting up multi-node environment (vllm-pr…
c051bfe 
…oject#6529)

[doc][distributed] add more doc for setting up multi-node environment (vllm-project#6529)
@DarkLight1337
[Misc] Manage HTTP connections in one place (vllm-project#6600)
97234be
@youkaichao
[misc] only tqdm for first rank (vllm-project#6672)
c520124
@ywang96
[VLM][Model] Support image input for Chameleon (vllm-project#6633)
22fa2e3
@simon-mo
support ignore patterns in model loader (vllm-project#6673)
3eda4ec
@simon-mo
Bump version to v0.5.3 (vllm-project#6674)
bb2fc08
@WoosukKwon
[Docs] Announce llama3.1 support (vllm-project#6688)
cb1362a
@youkaichao
[doc][distributed] fix doc argument order (vllm-project#6691)
71950af
@WoosukKwon
[Bugfix] Fix a log error in chunked prefill (vllm-project#6694)
461089a
@WoosukKwon
[BugFix] Fix RoPE error in Llama 3.1 (vllm-project#6693)
a112a84
@simon-mo
Bump version to 0.5.3.post1 (vllm-project#6696)
38c4b7e
@mgoin
[Misc] Add ignored layers for fp8 quantization (vllm-project#6657)
0eb0757
@yecohn
[Frontend] Add Usage data in each chunk for chat_serving. vllm-projec…
58f5303 
…t#6540 (vllm-project#6652)
@tjohnson31415
[Model] Pipeline Parallel Support for DeepSeek v2 (vllm-project#6519)
507ef78 
Signed-off-by: Travis Johnson <[email protected]>
@ywang96
Bump transformers version for Llama 3.1 hotfix and patch Chameleon (v…
1bedf21 
…llm-project#6690)
@youkaichao
[build] relax wheel size limit (vllm-project#6704)
72fc704
sgwhat and others added 30 commits August 6, 2024 21:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.