Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

merge from upstream #7

Merged
merged 48 commits into from
Apr 6, 2024
Merged

merge from upstream #7

merged 48 commits into from
Apr 6, 2024

Conversation

l3utterfly
Copy link
Owner

No description provided.

cebtenzzre and others added 30 commits March 28, 2024 11:44
* Revisited & updated SYCL build documentation

* removed outdated comment

* Addressed PR comments

* Trimed white spaces

* added new end line
* Allow conversion of Mistral HF models

* Homogenize Llama, Mistral, Mixtral under the same entry.

* Fix tokenizer, permute tensors

* Use sentencepiece tokenizer, or fall back to hfft.

* convert-hf : small fix for mypy

* convert-hf : fix duplicated block_count

* convert-hf : add vocab size to metadata

---------

Co-authored-by: Jared Van Bortel <[email protected]>
* llama: remove redundant reshape in build_kv_store

This commit removes the reshape of the V matrix in the build_kv_store.

The motivation for this is that V matrix has the shape:
```console
(gdb) p *v_cur
$46 = {type = GGML_TYPE_F32, backend = GGML_BACKEND_TYPE_CPU,
       buffer = 0x0, ne = {4096, 512, 1, 1}, nb = {4, 16384, 8388608,
       8388608}, op = GGML_OP_MUL_MAT, op_params = {
       0 <repeats 16 times>}, flags = 0, grad = 0x0,
       src = {0xb496b0, 0x7ffef1c40950, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
       0x0, 0x0}, perf_runs = 0, perf_cycles = 0, perf_time_us = 0,
       view_src = 0x0, view_offs = 0, data = 0x0,
       name = "Vcur-0", '\000' <repeats 57 times>, extra = 0x0,
       padding = "\000\000\000\000\000\000\000"}
```
And after reshaping this tensor we get:
```console
gdb) p *ggml_reshape_2d(ctx, v_cur, n_embd_v_gqa, n_tokens)
$44 = {type = GGML_TYPE_F32, backend = GGML_BACKEND_TYPE_CPU,
       buffer = 0x0, ne = {4096, 512, 1, 1}, nb = {4, 16384, 8388608,
       8388608}, op = GGML_OP_RESHAPE, op_params = {
       0 <repeats 16 times>}, flags = 0, grad = 0x0,
       src = {0x7ffef1c40e00, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
       0x0}, perf_runs = 0, perf_cycles = 0, perf_time_us = 0,
       view_src = 0x7ffef1c40e00, view_offs = 0, data = 0x0,
       name = "Vcur-0 (reshaped)", '\000' <repeats 46 times>, extra = 0x0,
       padding = "\000\000\000\000\000\000\000"}
```
I noticed that the `src` and `view_src` fields are different but that the
dimensions are the same. From the code comment it seems like the reshape
call is not needed and perhaps the above can motivate the removal of the
reshape call.

Signed-off-by: Daniel Bevenius <[email protected]>

* llama : add assert

---------

Signed-off-by: Daniel Bevenius <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>
* cmake: add explicit metal version options

* Update CMakeLists.txt

---------

Co-authored-by: Georgi Gerganov <[email protected]>
* readme: add Android UI binding

* Update README.md
* Support xverse model convert to gguf format.

* 1. Convert xverse models to gguf;
2. Add LLM_ARCH_XVERSE inference in llama.cpp;
3. Add xverse item in Supported models in README.md;

* * gguf-py: remove redundant logs
* llama: remove the init_mapping_prefetch custom parameter

* llama.cpp: Include the changes from ggerganov#6122 to exclude the unused outputs of the last layers.

* - Fix format issues
- Remove duplicate set kqv_out to llm_build_kv

* Update llama.cpp

---------

Co-authored-by: willhe <[email protected]>
Co-authored-by: willhe <[email protected]>
* sync : ggml

ggml-ci

* cuda : move GGML_CUDA_DMMV constants to dmmv.cuh

---------

Co-authored-by: slaren <[email protected]>
…6155)

* Fix Vulkan no kv offload incoherence

* Add k-quant mul mat mat shaders

* Rework working buffer allocation, reduces vram use noticeably

Clean up cpu assist code, replaced with ggml-backend offload function

* Default to all dedicated GPUs

* Add fallback for integrated GPUs if no dedicated GPUs are found

* Add debug info which device is allocating memory

* Fix Intel dequant issue

Fix validation issue

* Fix Vulkan GGML_OP_GET_ROWS implementation

* Clean up merge artifacts

* Remove Vulkan warning
* split by max size

* clean up arg parse

* split: ok

* add dry run option

* error on 0 tensors

* be positive

* remove next_metadata_size
* fixed deprecated address

* fixed deprecated address

* fixed deprecated address

* Added 'Apache-2.0' SPDX license identifier due to 'kompute.cc' submodule licensing. Explanation of licensing method: https://docs.fedoraproject.org/en-US/legal/spdx/#_and_expressions

* Added 'Apache-2.0' SPDX license identifier due to 'kompute.cc' submodule licensing. Explanation of licensing method: https://docs.fedoraproject.org/en-US/legal/spdx/#_and_expressions

* Added 'Apache-2.0' SPDX license identifier due to 'kompute.cc' submodule licensing. Explanation of licensing method: https://docs.fedoraproject.org/en-US/legal/spdx/#_and_expressions

* reverted back to only the MIT license
* ci: server: verify deps are coherent with the commit

* ci: server: change the ref to build as now it's a pull event target
Flake lock file updates:

• Updated input 'nixpkgs':
    'github:NixOS/nixpkgs/44d0940ea560dee511026a53f0e2e2cde489b4d4' (2024-03-23)
  → 'github:NixOS/nixpkgs/d8fe5e6c92d0d190646fb9f1056741a229980089' (2024-03-29)

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* disable iqx on windows as WA

* array instead of global_memory
…6387)

* ggml : update mul_mat_id to use the same tensor for all the experts

* update cuda

* minor

* update metal

* update test-backend-ops

* fix cuda

* Update ggml-metal.m

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

* update convert.py

* update convert-hf-to-gguf.py

* update convert.py for mixtral hf models

* Update convert-hf-to-gguf.py

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

* cuda : support non-pow-2 number of experts

* allow quantize to work for split and merged experts models in the same way

* cleanup + disable mmap automatically with split tensors models

* update imatrix

* test-backend-ops : test qwen argsort

* update grok model loading

* llama : add merged experts tensors to the grok tensor map

* minor

* gguf : bump version

* fix quantizing of merged experts

* convert-hf-to-gguf.py : update grok (untested)

* make linter happy

* cuda/argsort : use shared memory instead of pool memory

* convert : fix grok tensor names

* metal : add support for non-pow-2 argsort

* llama : more loader cleanup, better error checking

* cuda : fix warning

* llama : still use mmap for loading old models, but copy the data to a host buffer

* add review note

* llama : remove ffn tensor counting + add sanity check

ggml-ci

* convert : fix handling of n_experts == None

ggml-ci

* imatrix : fix ncall counters

* llama : produce error if imatrix size does not match

* quantize : terminate on errors + trace logs

ggml-ci

* metal : pad shared memory to 16 bytes

---------

Co-authored-by: Georgi Gerganov <[email protected]>
* Add openchat chat template

* Add chat template test for openchat

* Add chat template for vicuna

* Add chat template for orca-vicuna

* Add EOS for vicuna templates

* Combine vicuna chat templates

* Add tests for openchat and vicuna chat templates

* Add chat template for alpaca

* Add separate template name for vicuna-orca

* Remove alpaca, match deepseek with jinja output

* Regenerate chat template test with add_generation_prompt

* Separate deepseek bos from system message

* Match openchat template with jinja output

* Remove BOS token from templates, unprefix openchat
* Create SECURITY.md

Signed-off-by: Joyce <[email protected]>

* Fix: link on SECURITY.md

Signed-off-by: Joyce <[email protected]>

* Fix: link on SECURITY.md

Signed-off-by: Joyce <[email protected]>

* minor

* fix

* fix

---------

Signed-off-by: Joyce <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>
…rganov#6456)

* CI: Update actions/checkout to v4

* CI: Update actions/setup-python to v5

* CI: Update actions/upload-artifact to v4
* initial commit for sealion support

* add sealion support

* minor fix

* q/k ln and pos_embd only if required

* Apply suggestions from code review

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

* minor : clear whitespaces

---------

Co-authored-by: bryan <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>
* Typo fix to server's README.md

Fix minor typo ("tonen") in server README.

* server readme grammar/style fixes.

Quickly went through this file to look for inconsistencies in
presentation of defaults, flag options, and looked for typos
and grammar issues.

Not perfect, but hopefully improved.

* Update README.md

Remove an extra space before newline.
HanClinto and others added 18 commits April 4, 2024 09:32
* Revising GBNF validator program to be much simpler.

* Changing from streams to using cstdio

* Adding final newline character.
This commit removes one of the two identical checks for curl being NULL
in llama_load_model_from_url.

Signed-off-by: Daniel Bevenius <[email protected]>
* ci: bench: change trigger path to not spawn on each PR

* ci: bench: add more file type for phi-2: q8_0 and f16.
- do not show the comment by default

* ci: bench: add seed parameter in k6 script

* ci: bench: artefact name perf job

* Add iteration in the commit status, reduce again the autocomment

* ci: bench: add per slot metric in the commit status

* Fix trailing spaces
README is called README.md.
Name the artifacts in the build CI, so that they get uploaded with separate names, instead of all put into the same `artifact` ZIP.

It might be possible to further simplify the packing step (in future PRs).
…6486)

* ci: exempt master branch workflows from getting cancelled

* apply to bench.yml
* server: add cURL support to `full.Dockerfile`

* server: add cURL support to `full-cuda.Dockerfile` and `server-cuda.Dockerfile`

* server: add cURL support to `full-rocm.Dockerfile` and `server-rocm.Dockerfile`

* server: add cURL support to `server-intel.Dockerfile`

* server: add cURL support to `server-vulkan.Dockerfile`

* fix typo in `server-vulkan.Dockerfile`

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

---------

Co-authored-by: Georgi Gerganov <[email protected]>
…ganov#6464)

* moved INTEL_MKL guard from gemm_impl to gemm (wrapper)

* Update ggml-sycl.cpp

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

---------

Co-authored-by: AidanBeltonS <[email protected]>
…ganov#6500)

* bench: make n_batch and n_ubatch configurable

* bench: update doc for batched bench
* Add MindMac to UI list

* Update proprietary description

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

---------

Co-authored-by: slaren <[email protected]>
@l3utterfly l3utterfly merged commit 607bb9a into layla-build Apr 6, 2024
46 of 61 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.