b3614

llama : simplify Mamba with advanced batch splits (#8526)

* llama : advanced batch splits

This includes equal-sequence-length batch splits which are useful
to simplify recurrent model operators.

* llama : always make recurrent state slots contiguous

* ggml : simplify mamba operators

* llama : fix integer signedness mixing

* llama : logits_all has priority over batch->logits

Otherwise, the server embeddings tests failed.
This was likely an existing problem but was only detected here
because of an additional assertion.

* llama : apply suggestions

Co-authored-by: Georgi Gerganov <[email protected]>

* llama : fix t5 segfault

* llama : fix Mamba session save and restore

* llama : minor cosmetic changes

* llama : rename llama_reorder_outputs to llama_output_reorder

Also move it closer to llama_output_reserve.

* llama : fix pooled embeddings when using batches with equal_seqs

* minor : add struct members for clarity

ggml-ci

* llama : fix T5 segfault again

* llama : fix Mamba pooled embeddings with multiple sequences

Until the pooled embeddings are refactored to allow splitting
across ubatches for causal embeddings,
recurrent models can only process a single sequence per ubatch
when calculating pooled embeddings.

* llama : add llama_model_is_recurrent to simplify figuring that out

This will make it easier to more cleanly support RWKV-v6 and Mamba-2.

* llama : fix simple splits when the batch contains embeddings

---------

Co-authored-by: Georgi Gerganov <[email protected]>

b3608

[SYCL] fallback mmvq (#9088)

* fallback mmvq to mul_mat

* mmvq in cuda path

* Update ggml/src/ggml-sycl.cpp

Co-authored-by: Alberto Cabrera Pérez <[email protected]>

---------

Co-authored-by: Alberto Cabrera Pérez <[email protected]>

b3605

cann: add doc for cann backend (#8867)

Co-authored-by: xuedinge233 <[email protected]>
Co-authored-by: hipudding <[email protected]>

b3599

server : refactor middleware and /health endpoint (#9056)

* server : refactor middleware and /health endpoint

* move "fail_on_no_slot" to /slots

* Update examples/server/server.cpp

Co-authored-by: Georgi Gerganov <[email protected]>

* fix server tests

* fix CI

* update server docs

---------

Co-authored-by: Georgi Gerganov <[email protected]>

b3590

retrieval : fix memory leak in retrieval query handling (#8955)

* retrieval

* Reuse querybatch to reduce frequent memory allocation

* delete unused white space

b3584

Vulkan Optimizations and Fixes (#8959)

* Optimize Vulkan REPEAT performance

* Use Vulkan GLSL fused multiply-add instruction where possible

* Add GGML_VULKAN_PERF option to output performance data per operator

* Rework and fix Vulkan descriptor set and descriptor pool handling

* Fix float32 concat f16 shader validation error

* Add Vulkan GROUP_NORM eps parameter

* Fix validation error with transfer queue memory barrier flags

* Remove trailing whitespaces

b3581

ggml : move rope type enum to ggml.h (#8949)

* ggml : move rope type enum to ggml.h

This commit moves the `llama_rope_type` enum from `llama.h` to
`ggml.h` and changes its name to `ggml_rope_type`.

The motivation for this change is to address the TODO in `llama.h` and
use the enum in ggml.

Note: This commit does not change the `mode` parameter to be of type
`enum ggml_rope_type`. The name `mode` and its usage suggest that it
might be more generic and possibly used as a bit field for multiple
flags. Further investigation/discussion may be needed to determine
if `mode` should be restricted to RoPE types.

* squash! ggml : move rope type enum to ggml.h

This commit removes GGML_ROPE_TYPE_NONE and GGML_ROPE_TYPE_GLM from
ggml.h, and back the llama_rope_type enum.

I've kept the assert for GGML_ROPE_TYPE_GLM as I'm not sure if it is
safe to remove it yet.

* squash! ggml : move rope type enum to ggml.h

This commit removes the enum ggml_rope_type from ggml.h and replaces it
with a define (GGML_ROPE_TYPE_NEOX). This define is used in the code to
check if the mode is set to GPT-NeoX. Also the enum llama_rope_type has
been updated to reflect this change.

* squash! ggml : move rope type enum to ggml.h

This commit contains a suggestion enable the GGML_ROPE_TYPE_NEOX
macro/define to be passed to the shader compiler.

* squash! ggml : move rope type enum to ggml.h

This commit fixes the editorconfig-checker warnings.

* squash! ggml : move rope type enum to ggml.h

Update comment for ggml_rope function.

* Revert "squash! ggml : move rope type enum to ggml.h"

This reverts commit 6261222bd0dc0efd51f0fb0435ad3f16a5b52fd6.

* squash! ggml : move rope type enum to ggml.h

Add GGML_ROPE_TYPE_NEOX to rope_common.comp.

* remove extra line

---------

Co-authored-by: slaren <[email protected]>

b3580

export-lora : throw error if lora is quantized (#9002)

b3570

gguf-py : Numpy dequantization for most types (#8939)

* gguf-py : Numpy dequantization for most types

* gguf-py : Numpy dequantization for grid-based i-quants

b3541

ggml-backend : fix async copy from CPU (#8897)

* ggml-backend : fix async copy from CPU

* cuda : more reliable async copy, fix stream used when the devices are the same