minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Remove deprecated Mamba flags from doc, wrong FP8 GEMM docstrings and change Nemotron image to 0.5.15 (#31094)

Browse Source 
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
This commit is contained in:
Brayden Zhong
2026-07-17 14:34:29 -07:00
committed by GitHub
co-authored by Brayden Zhong
parent c00206c68c
commit 7fc3fb9657
24 changed files with 46 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/server_args.py
+4 -4
View File
@@ -1427,7 +1427,7 @@ class ServerArgs:
fp8_gemm_runner_backend: A[
str,
Arg(
help="Choose the runner backend for Blockwise FP8 GEMM operations. Options: 'auto' (default, auto-selects based on hardware), 'deep_gemm' (JIT-compiled; enabled by default on NVIDIA Hopper (SM90) and Blackwell (SM100) when DeepGEMM is installed), 'flashinfer_trtllm' (optimal for Blackwell and low-latency), 'flashinfer_cutlass' (FlashInfer CUTLASS groupwise FP8 GEMM), 'flashinfer_deepgemm' (Hopper SM90 only; uses swapAB optimization for small M dimensions in decoding), 'cutlass' (optimal for Hopper/Blackwell GPUs and high-throughput), 'triton' (fallback, widely compatible), 'aiter' (ROCm only). ",
help="Choose the runner backend for Blockwise FP8 GEMM operations. Options: 'auto' (default, auto-selects based on hardware), 'deep_gemm' (JIT-compiled; enabled by default on NVIDIA Hopper (SM90) and Blackwell (SM100) when DeepGEMM is installed), 'flashinfer_trtllm' (optimal for Blackwell and low-latency), 'flashinfer_cutlass' (FlashInfer CUTLASS groupwise FP8 GEMM), 'flashinfer_deepgemm' (Hopper SM90 only; uses swapAB optimization for small M dimensions in decoding), 'cutlass' (optimal for SM120 GPUs), 'triton' (fallback, widely compatible), 'aiter' (ROCm only). ",
cli_name="--fp8-gemm-backend",
choices=FP8_GEMM_RUNNER_BACKEND_CHOICES,
resolvable=True,
@@ -2136,7 +2136,7 @@ class ServerArgs:
"baseline (the per-K g_cache is K x larger and the reconstruction "
"refolds the per-K decay every step), so it is not recommended for KDA "
"models. Requires the Triton linear-attn decode backend and "
"--mamba-scheduler-strategy no_buffer (the default).",
"--mamba-radix-cache-strategy no_buffer (the default).",
] = False
linear_replayssm_cache_len: A[
int,
@@ -5221,10 +5221,10 @@ class ServerArgs:
if mamba_extra_buffer_of(resolved_view(self)):
raise ValueError(
"--enable-linear-replayssm requires --mamba-scheduler-strategy "
"--enable-linear-replayssm requires --mamba-radix-cache-strategy "
"no_buffer (the default); the extra_buffer ping-pong "
"donation path is not yet supported (follow-up). Got "
f"--mamba-scheduler-strategy={self.mamba_scheduler_strategy!r}."
f"--mamba-radix-cache-strategy={self.mamba_radix_cache_strategy!r}."
)
if self.disaggregation_mode != "null":
# The disaggregated decode pool (HybridMambaDecodeReqToTokenPool)