Open
Conversation
- Add INT4 W4A16 MoE config for E=384,N=128 (Kimi K2.5) - Add FP8 W8A8 configs for AMD Instinct MI300X - Update fused_moe_triton layer for W4A16 support - Update compressed_tensors_moe for INT4 quantization - Add HIP kernels for ROCm support
Feature: Support torch compile for Kimi-K2.5
Changes: - kimi_k25.py: Add pp_proxy_tensors parameter to forward method and pass it to general_mm_embed_routine - deepseek_v2.py: Fix device acquisition for non-first PP rank when input_embeds and input_ids are both None Tested with TP=4, PP=2 configuration: - Prefill test: 10 requests, 100% success - Decode test: 20 requests, 100% success
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Modifications
Accuracy Tests
Benchmarking and Profiling
Checklist
Review Process
/tag-run-ci-label,/rerun-failed-ci,/tag-and-rerun-ci