Update ROCm vLLM to 0.4.3 #40
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: Robert Shaw <[email protected]> Co-authored-by: Robert Shaw <[email protected]>
…project#3922) Co-authored-by: alexm <[email protected]> Co-authored-by: mgoin <[email protected]>
…ect#4165) Co-authored-by: Lei Wen <[email protected]>
Signed-off-by: Prashant Gupta <[email protected]> Co-authored-by: Roger Wang <[email protected]>
Co-authored-by: Philipp Moritz <[email protected]> Co-authored-by: Woosuk Kwon <[email protected]> Co-authored-by: mgoin <[email protected]> Co-authored-by: Tyler Michael Smith <[email protected]> Co-authored-by: Cody Yu <[email protected]>
…int (vllm-project#3467) Co-authored-by: Lily Liu <[email protected]> Co-authored-by: Cyrus Leung <[email protected]>
…vllm-project#4494) Co-authored-by: Simon Mo <[email protected]>
… obtain the CUDA version. (vllm-project#4173) Signed-off-by: AnyISalIn <[email protected]>
…#5112) Co-authored-by: Alexey Kondratiev <[email protected]> Co-authored-by: Alexei-V-Ivanov-AMD <[email protected]> Co-authored-by: Alexei V. Ivanov <[email protected]> Co-authored-by: omkarkakarparthi <okakarpa>
Co-authored-by: Breno Faria <[email protected]>
Co-authored-by: Roger Wang <[email protected]>
…red_metadata modifier (introduced with PTX 8.5) (vllm-project#5136)
Co-authored-by: Zhuohan Li <[email protected]>
…e ::ordered_metadata modifier (introduced with PTX 8.5)" (vllm-project#5149)
Co-authored-by: xuhao <[email protected]>
Updated the base docker to ROCm 6.1.1 Updated the RCCL pin to a new one with performance improvements
…thub.com/vllm-project/vllm into main_upstream_candidate_531
Partially reverts [Core][Distributed] use cpu group to broadcast metadata in cpu (vllm-project#4444)
initial commit for v0.4.0 with paged attn optimization update the integration code updates to custom attention kenrel update unit test case for custom update conditions to pick paged attn v2 vs custom update env condition enable more parameters in custom unit testing update conditions for custom vs v2 update gqa ratio condition for using custom kernel updated docs, cleanup and enabled it by default fixes imports for custom paged attn update the custom paged attn with latest data update conditions of max-context-len
Fix bias handling with tgemm Don't use custom matvec kernel for bf16
fp8 computation Using convert_fp8 kernel delete convert.cu clean up clean up remove extra kernels remove int8 -> fp8 convert fix naming fix typo clean up add compilation guard add convert_fp8 in cache_ops clean up adding missing quant config back fix the convert_fp8 issue convert_fp8 fix fix
Restore use of FA Triton as default update base docker image remove apply_custom Use inp_view for out = F.linear() in TunedGemm (#36) * use inp_view for out = F.linear() * add missing control path fix
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.
Bring in upstream vLLM changes as of May 31 into ROCm/vllm
Updates ROCm vLLM to 0.4.3