Skip to content

Commit 2392503

Browse files
committed
[skip ci] Update nightly support matrices
Signed-off-by: Buildkite Bot <buildkite-bot@users.noreply.github.com>
1 parent 62763b5 commit 2392503

File tree

2 files changed

+5
-5
lines changed

2 files changed

+5
-5
lines changed

support_matrices/nightly/feature_support_matrix.csv

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,10 +3,10 @@ Feature,CorrectnessTest,PerformanceTest
33
"Chunked Prefill",✅,✅
44
"Structured Decoding",❌,N/A
55
"Single Program Multi Data",✅,✅
6-
"Quantized Matmul Attention and KV Cache",✅,
6+
"Quantized Matmul Attention and KV Cache",✅,
77
"JAX-Path Qxix Quantization",✅,❌
88
"Multimodal Inputs",❌,N/A
9-
"async scheduler",✅,✅
9+
"async scheduler",❌,N/A
1010
"Speculative Decoding: Ngram",❌,N/A
1111
"Collective Communication Matmul",❌,N/A
1212
"Ragged Paged Attention V3",✅,✅
Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,8 @@
11
Model,UnitTest,IntegrationTest,Benchmark
2-
"meta-llama/Llama-3.3-70B-Instruct",✅,✅,❌
2+
"meta-llama/Llama-3.3-70B-Instruct",❌,N/A,N/A
33
"Qwen/Qwen3-4B",❌,N/A,N/A
44
"Qwen/Qwen2.5-VL-7B-Instruct",❌,N/A,N/A
5-
"google/gemma-3-27b-it",✅,✅,
6-
"Qwen/Qwen3-32B",✅,✅,❌
5+
"google/gemma-3-27b-it",✅,✅,
6+
"Qwen/Qwen3-32B",❌,N/A,N/A
77
"meta-llama/Llama-3.1-8B-Instruct",❌,N/A,N/A
88
"Qwen/Qwen3-30B-A3B",❌,N/A,N/A

0 commit comments

Comments
 (0)