sglang 0.4.1.post2__tar.gz → 0.4.1.post4__tar.gz

{sglang-0.4.1.post2 → sglang-0.4.1.post4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sglang
-Version: 0.4.1.post2
+Version: 0.4.1.post4
 Summary: SGLang is yet another fast serving framework for large language models and vision language models.
 License:                                  Apache License
                                    Version 2.0, January 2004
@@ -243,11 +243,11 @@ Requires-Dist: torch; extra == "srt"
 Requires-Dist: vllm<=0.6.4.post1,>=0.6.3.post1; extra == "srt"
 Requires-Dist: cuda-python; extra == "srt"
 Requires-Dist: flashinfer==0.1.6; extra == "srt"
-Requires-Dist: sgl-kernel>=0.0.2.post10; extra == "srt"
+Requires-Dist: sgl-kernel>=0.0.2.post11; extra == "srt"
 Provides-Extra: srt-hip
 Requires-Dist: sglang[runtime_common]; extra == "srt-hip"
 Requires-Dist: torch; extra == "srt-hip"
-Requires-Dist: vllm==0.6.3.dev13; extra == "srt-hip"
+Requires-Dist: vllm==0.6.3.post2.dev1; extra == "srt-hip"
 Provides-Extra: srt-xpu
 Requires-Dist: sglang[runtime_common]; extra == "srt-xpu"
 Provides-Extra: srt-hpu
@@ -315,7 +315,7 @@ Requires-Dist: sglang[test]; extra == "dev-hpu"
 
 | [**Blog**](https://lmsys.org/blog/2024-07-25-sglang-llama3/)
 | [**Documentation**](https://sgl-project.github.io/)
-| [**Join Slack**](https://join.slack.com/t/sgl-fru7574/shared_invite/zt-2tmmp6flg-89dOlJW2TjnBrTRk1I_~GA)
+| [**Join Slack**](https://join.slack.com/t/sgl-fru7574/shared_invite/zt-2um0ad92q-LkU19KQTxCGzlCgRiOiQEw)
 | [**Join Bi-Weekly Development Meeting**](https://docs.google.com/document/d/1xEow4eIM152xNcRxqZz9VEcOiTQo8-CEuuQ5qTmkt-E/edit?usp=sharing)
 | [**Slides**](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#slides) |
 
@@ -347,9 +347,10 @@ The core features include:
 
 ## Getting Started
 - [Install SGLang](https://sgl-project.github.io/start/install.html)
-- [Send requests](https://sgl-project.github.io/start/send_request.html)
-- [Backend: SGLang Runtime (SRT)](https://sgl-project.github.io/backend/backend.html)
-- [Frontend: Structured Generation Language (SGLang)](https://sgl-project.github.io/frontend/frontend.html)
+- [Quick Start](https://sgl-project.github.io/start/send_request.html)
+- [Backend Tutorial](https://sgl-project.github.io/backend/openai_api_completions.html)
+- [Frontend Tutorial](https://sgl-project.github.io/frontend/frontend.html)
+- [Contribution Guide](https://sgl-project.github.io/references/contribution_guide.html)
 
 ## Benchmark and Performance
 Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3 blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/), [v0.4 blog](https://lmsys.org/blog/2024-12-04-sglang-v0-4/)
@@ -361,5 +362,5 @@ Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-s
 The project is supported by (alphabetically): AMD, Baseten, DataCrunch, Etched, Hyperbolic, Jam & Tea Studios, LinkedIn, LMSYS.org, Meituan, NVIDIA, RunPod, Stanford, UC Berkeley, UCLA, xAI, 01.AI.
 
 ## Acknowledgment and Citation
-We learned from the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).
+We learned the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).
 Please cite the paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.

{sglang-0.4.1.post2 → sglang-0.4.1.post4}/README.md

@@ -14,7 +14,7 @@
 
 | [**Blog**](https://lmsys.org/blog/2024-07-25-sglang-llama3/)
 | [**Documentation**](https://sgl-project.github.io/)
-| [**Join Slack**](https://join.slack.com/t/sgl-fru7574/shared_invite/zt-2tmmp6flg-89dOlJW2TjnBrTRk1I_~GA)
+| [**Join Slack**](https://join.slack.com/t/sgl-fru7574/shared_invite/zt-2um0ad92q-LkU19KQTxCGzlCgRiOiQEw)
 | [**Join Bi-Weekly Development Meeting**](https://docs.google.com/document/d/1xEow4eIM152xNcRxqZz9VEcOiTQo8-CEuuQ5qTmkt-E/edit?usp=sharing)
 | [**Slides**](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#slides) |
 
@@ -46,9 +46,10 @@ The core features include:
 
 ## Getting Started
 - [Install SGLang](https://sgl-project.github.io/start/install.html)
-- [Send requests](https://sgl-project.github.io/start/send_request.html)
-- [Backend: SGLang Runtime (SRT)](https://sgl-project.github.io/backend/backend.html)
-- [Frontend: Structured Generation Language (SGLang)](https://sgl-project.github.io/frontend/frontend.html)
+- [Quick Start](https://sgl-project.github.io/start/send_request.html)
+- [Backend Tutorial](https://sgl-project.github.io/backend/openai_api_completions.html)
+- [Frontend Tutorial](https://sgl-project.github.io/frontend/frontend.html)
+- [Contribution Guide](https://sgl-project.github.io/references/contribution_guide.html)
 
 ## Benchmark and Performance
 Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3 blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/), [v0.4 blog](https://lmsys.org/blog/2024-12-04-sglang-v0-4/)
@@ -60,5 +61,5 @@ Learn more in our release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-s
 The project is supported by (alphabetically): AMD, Baseten, DataCrunch, Etched, Hyperbolic, Jam & Tea Studios, LinkedIn, LMSYS.org, Meituan, NVIDIA, RunPod, Stanford, UC Berkeley, UCLA, xAI, 01.AI.
 
 ## Acknowledgment and Citation
-We learned from the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).
+We learned the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).
 Please cite the paper, [SGLang: Efficient Execution of Structured Language Model Programs](https://arxiv.org/abs/2312.07104), if you find the project useful.

{sglang-0.4.1.post2 → sglang-0.4.1.post4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sglang"
-version = "0.4.1.post2"
+version = "0.4.1.post4"
 description = "SGLang is yet another fast serving framework for large language models and vision language models."
 readme = "README.md"
 requires-python = ">=3.8"
@@ -23,11 +23,11 @@ runtime_common = ["aiohttp", "decord", "fastapi",
     "psutil", "pydantic", "python-multipart",
     "pyzmq>=25.1.2", "torchao>=0.7.0", "uvicorn", "uvloop",
     "xgrammar>=0.1.6"]
-srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1", "cuda-python", "flashinfer==0.1.6", "sgl-kernel>=0.0.2.post10"]
+srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1", "cuda-python", "flashinfer==0.1.6", "sgl-kernel>=0.0.2.post11"]
 
 # HIP (Heterogeneous-computing Interface for Portability) for AMD
 # => base docker rocm/vllm-dev:20241022, not from public vllm whl
-srt_hip = ["sglang[runtime_common]", "torch", "vllm==0.6.3.dev13"]
+srt_hip = ["sglang[runtime_common]", "torch", "vllm==0.6.3.post2.dev1"]
 # xpu is not enabled in public vllm and torch whl,
 # need to follow https://docs.vllm.ai/en/latest/getting_started/xpu-installation.htmlinstall vllm
 srt_xpu = ["sglang[runtime_common]"]
@@ -61,7 +61,7 @@ dev_hpu = ["sglang[all_hpu]", "sglang[test]"]
 "Bug Tracker" = "https://github.com/sgl-project/sglang/issues"
 
 [tool.setuptools.package-data]
-"sglang" = ["srt/layers/fused_moe_triton/configs/*.json"]
+"sglang" = ["srt/layers/moe/fused_moe_triton/configs/*.json", "srt/layers/quantization/configs/*.json"]
 
 [tool.setuptools.packages.find]
 exclude = [

{sglang-0.4.1.post2 → sglang-0.4.1.post4}/sglang/bench_one_batch.py

@@ -63,6 +63,7 @@ from sglang.srt.model_executor.model_runner import ModelRunner
 from sglang.srt.sampling.sampling_params import SamplingParams
 from sglang.srt.server import _set_envs_and_config
 from sglang.srt.server_args import PortArgs, ServerArgs
+from sglang.srt.speculative.spec_info import SpeculativeAlgorithm
 from sglang.srt.utils import configure_logger, kill_process_tree, suppress_other_loggers
 
 
@@ -214,6 +215,7 @@ def extend(reqs, model_runner):
         tree_cache=None,
         model_config=model_runner.model_config,
         enable_overlap=False,
+        spec_algorithm=SpeculativeAlgorithm.NONE,
     )
     batch.prepare_for_extend()
     model_worker_batch = batch.get_model_worker_batch()

{sglang-0.4.1.post2 → sglang-0.4.1.post4}/sglang/srt/layers/attention/__init__.py

@@ -1,10 +1,14 @@
+from __future__ import annotations
+
 from abc import ABC, abstractmethod
-from typing import Optional
+from typing import TYPE_CHECKING, Optional
 
 import torch
 
-from sglang.srt.layers.radix_attention import RadixAttention
-from sglang.srt.model_executor.forward_batch_info import ForwardBatch
+if TYPE_CHECKING:
+    from sglang.srt.layers.radix_attention import RadixAttention
+    from sglang.srt.model_executor.forward_batch_info import ForwardBatch, ForwardMode
+    from sglang.srt.speculative.spec_info import SpecInfo
 
 
 class AttentionBackend(ABC):
@@ -22,9 +26,12 @@ class AttentionBackend(ABC):
     def init_forward_metadata_capture_cuda_graph(
         self,
         bs: int,
+        num_tokens: int,
         req_pool_indices: torch.Tensor,
         seq_lens: torch.Tensor,
-        encoder_lens: Optional[torch.Tensor] = None,
+        encoder_lens: Optional[torch.Tensor],
+        forward_mode: ForwardMode,
+        spec_info: Optional[SpecInfo],
     ):
         """Init the metadata for a forward pass for capturing a cuda graph."""
         raise NotImplementedError()
@@ -35,7 +42,9 @@ class AttentionBackend(ABC):
         req_pool_indices: torch.Tensor,
         seq_lens: torch.Tensor,
         seq_lens_sum: int,
-        encoder_lens: Optional[torch.Tensor] = None,
+        encoder_lens: Optional[torch.Tensor],
+        forward_mode: ForwardMode,
+        spec_info: Optional[SpecInfo],
     ):
         """Init the metadata for a forward pass for replying a cuda graph."""
         raise NotImplementedError()

{sglang-0.4.1.post2 → sglang-0.4.1.post4}/sglang/srt/layers/attention/double_sparsity_backend.py

@@ -3,7 +3,6 @@ from __future__ import annotations
 from typing import TYPE_CHECKING
 
 import torch
-import torch.nn as nn
 
 from sglang.srt.layers.attention import AttentionBackend
 from sglang.srt.managers.schedule_batch import global_server_args_dict
@@ -52,8 +51,6 @@ class DoubleSparseAttnBackend(AttentionBackend):
 
         self.forward_metadata = None
 
-        self.cuda_graph_max_seq_len = model_runner.model_config.context_len
-
     def init_forward_metadata(self, forward_batch: ForwardBatch):
         """Init auxiliary variables for triton attention backend."""
 
@@ -115,55 +112,6 @@ class DoubleSparseAttnBackend(AttentionBackend):
             ds_req_to_token,
         )
 
-    def init_cuda_graph_state(self, max_bs: int):
-        # TODO(Andy): Support CUDA graph for double sparse attention
-        raise ValueError(
-            "Double sparse attention does not support CUDA graph for now. Please --disable-cuda-graph"
-        )
-        self.cuda_graph_max_total_num_tokens = max_bs * self.cuda_graph_max_seq_len
-
-        self.cuda_graph_start_loc = torch.zeros(
-            (max_bs,), dtype=torch.int32, device="cuda"
-        )
-        self.cuda_graph_attn_logits = torch.empty(
-            (
-                self.num_head,
-                self.cuda_graph_max_total_num_tokens,
-            ),
-            dtype=self.reduce_dtype,
-            device="cuda",
-        )
-
-    def init_forward_metadata_capture_cuda_graph(
-        self,
-        bs: int,
-        req_pool_indices: torch.Tensor,
-        seq_lens: torch.Tensor,
-        encoder_lens=None,
-    ):
-        # NOTE: encoder_lens expected to be zeros or None
-        self.forward_metadata = (
-            self.cuda_graph_start_loc,
-            self.cuda_graph_attn_logits,
-            self.cuda_graph_max_seq_len,
-            None,
-        )
-
-    def init_forward_metadata_replay_cuda_graph(
-        self,
-        bs: int,
-        req_pool_indices: torch.Tensor,
-        seq_lens: torch.Tensor,
-        seq_lens_sum: int,
-        encoder_lens=None,
-    ):
-        # NOTE: encoder_lens expected to be zeros or None
-        self.cuda_graph_start_loc.zero_()
-        self.cuda_graph_start_loc[1:bs] = torch.cumsum(seq_lens[: bs - 1], dim=0)
-
-    def get_cuda_graph_seq_len_fill_value(self):
-        return 1
-
     def forward_extend(
         self,
         q,