MCPcopy Create free account

hub / github.com/UCSB-AI/Soft-Thinking / endpoints

Endpoints79 in github.com/UCSB-AI/Soft-Thinking

⨍ Functions 6,405◇ Types & classes 1,237↳ Endpoints 79
Route_mul_attn_scale
torch.compile(dynamic=True, backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/models/llama4.py:None
Routeavailable_models
app.get("/v1/models", response_class=ORJSONResponse)
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routecancel_batches
app.post("/v1/batches/{batch_id}/cancel")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeclamp_position
torch.compile(dynamic=True, backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/model_executor/forward_batch_info.py:None
Routeclassify_request
app.api_route("/classify", methods=["POST", "PUT"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeclose_session
app.api_route("/close_session", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeconfigure_logging
app.api_route("/configure_logging", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routecopy_two_array
torch.compile(dynamic=True, backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/mem_cache/memory_pool.py:None
Routecustom_routing_function
torch.compile(dynamic=True, backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/models/llama4.py:None
Routedelete_file
app.delete("/v1/files/{file_id}")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routedump_expert_distribution_record_async
app.api_route("/dump_expert_distribution_record", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeencode_request
app.api_route("/encode", methods=["POST", "PUT"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeflush_cache
app.api_route("/flush_cache", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeflush_cache
app.post("/flush_cache")
sglang_soft_thinking_pkg/python/sglang/srt/disaggregation/mini_lb.py:None
Routegenerate
app.route("/generate", methods=["POST"])
sglang_soft_thinking_pkg/examples/runtime/engine/custom_server.py:None
Routegenerate_from_file_request
app.api_route("/generate_from_file", methods=["POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routegenerate_request
app.api_route("/generate", methods=["POST", "PUT"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routegenerate_stream
app.route("/generate_stream", methods=["POST"])
sglang_soft_thinking_pkg/examples/runtime/engine/custom_server.py:None
Routegenerate_text
app.post("/generate")
sglang_soft_thinking_pkg/examples/runtime/engine/fastapi_engine_inference.py:None
Routeget_last_loc
torch.compile(dynamic=True, backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/managers/schedule_batch.py:None
Routeget_model_info
app.get("/get_model_info")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeget_model_info
app.get("/get_model_info")
sglang_soft_thinking_pkg/python/sglang/srt/disaggregation/mini_lb.py:None
Routeget_models
app.get("/v1/models")
sglang_soft_thinking_pkg/python/sglang/srt/disaggregation/mini_lb.py:None
Routeget_server_info
app.get("/get_server_info")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeget_server_info
app.get("/get_server_info")
sglang_soft_thinking_pkg/python/sglang/srt/disaggregation/mini_lb.py:None
Routeget_weights_by_name
app.api_route("/get_weights_by_name", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routegrouped_topk
torch.compile(dynamic=True, backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/layers/moe/topk.py:None
Routehandle_completion_request
app.post("/v1/chat/completions")
sglang_soft_thinking_pkg/python/sglang/srt/disaggregation/mini_lb.py:None
Routehandle_generate_request
app.post("/generate")
sglang_soft_thinking_pkg/python/sglang/srt/disaggregation/mini_lb.py:None
Routehealth
app.get("/health")
sglang_soft_thinking_pkg/python/sglang/srt/utils.py:None
Routehealth
app.get("/health")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routehealth_check
app.get("/health")
sglang_soft_thinking_pkg/python/sglang/srt/disaggregation/mini_lb.py:None
Routehealth_generate
app.get("/health_generate")
sglang_soft_thinking_pkg/python/sglang/srt/utils.py:None
Routehealth_generate
app.get("/health_generate")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeinit_weights_update_group
app.post("/init_weights_update_group")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routelayer_norm_func
torch.compile(backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/models/commandr.py:None
Routeopen_session
app.api_route("/open_session", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeopenai_v1_batches
app.post("/v1/batches")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeopenai_v1_chat_completions
app.post("/v1/chat/completions")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeopenai_v1_completions
app.post("/v1/completions")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeopenai_v1_embeddings
app.post("/v1/embeddings", response_class=ORJSONResponse)
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeopenai_v1_files
app.post("/v1/files")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeparse_function_call_request
app.post("/parse_function_call")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routerelease_memory_occupation
app.api_route("/release_memory_occupation", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeresolve_future_token_ids
torch.compile(dynamic=True, backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/managers/tp_worker_overlap_thread.py:None
Routeresolve_future_topk_info
torch.compile(dynamic=True, backend=get_compiler_backend())
sglang_soft_thinking_pkg/python/sglang/srt/managers/tp_worker_overlap_thread.py:None
Routeresume_memory_occupation
app.api_route("/resume_memory_occupation", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeretrieve_batch
app.get("/v1/batches/{batch_id}")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeretrieve_file
app.get("/v1/files/{file_id}")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeretrieve_file_content
app.get("/v1/files/{file_id}/content")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routesagemaker_chat_completions
app.post("/invocations")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routesagemaker_health
app.get("/ping")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeseparate_reasoning_request
app.post("/separate_reasoning")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeset_internal_state
app.api_route("/set_internal_state", methods=["POST", "PUT"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routestart_expert_distribution_record_async
app.api_route("/start_expert_distribution_record", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routestart_profile_async
app.api_route("/start_profile", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routestop_expert_distribution_record_async
app.api_route("/stop_expert_distribution_record", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routestop_profile_async
app.api_route("/stop_profile", methods=["GET", "POST"])
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routetest_bmm_fp8
pytest.mark.parametrize("input_dtype", [torch.float8_e4m3fn, torch.float8_e5m2])
sglang_soft_thinking_pkg/sgl-kernel/tests/test_bmm_fp8.py:None
Routetest_init_new_standard_case
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_dp_rank
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_invalid_ipv6_address
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_ipv4_address
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_ipv6_address
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_malformed_ipv4_address
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_malformed_ipv4_address_invalid_port
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_malformed_ipv6_address_invalid_port
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_malformed_ipv6_address_missing_bracket
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_malformed_ipv6_address_missing_port
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_malformed_ipv6_address_wrong_separator
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_init_new_with_single_node_dp_attention
patch("sglang.srt.server_args.is_port_available")
sglang_soft_thinking_pkg/test/srt/test_server_args.py:None
Routetest_merge_attn_states
pytest.mark.parametrize("output_dtype", DTYPES)
sglang_soft_thinking_pkg/sgl-kernel/tests/test_merge_state_v2.py:None
Routetest_nvfp4_gemm
pytest.mark.skipif( skip_condition, reason="Nvfp4 Requires compute capability of 10 or above." )
sglang_soft_thinking_pkg/sgl-kernel/tests/test_fp4_gemm.py:None
Routetest_quantize_to_fp4
pytest.mark.skipif( skip_condition, reason="Nvfp4 Requires compute capability of 10 or above." )
sglang_soft_thinking_pkg/sgl-kernel/tests/test_fp4_quantize.py:None
Routetest_quantize_to_fp4_padded
pytest.mark.skipif( skip_condition, reason="Nvfp4 Requires compute capability of 10 or above." )
sglang_soft_thinking_pkg/sgl-kernel/tests/test_fp4_quantize.py:None
Routeupdate_weights_from_disk
app.post("/update_weights_from_disk")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeupdate_weights_from_distributed
app.post("/update_weights_from_distributed")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routeupdate_weights_from_tensor
app.post("/update_weights_from_tensor")
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None
Routevertex_generate
app.post(os.environ.get("AIP_PREDICT_ROUTE", "/vertex_generate"))
sglang_soft_thinking_pkg/python/sglang/srt/entrypoints/http_server.py:None