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

metal : add BF16 support #8439

Merged
merged 7 commits into from
Nov 6, 2024
Merged

metal : add BF16 support #8439

merged 7 commits into from
Nov 6, 2024

Conversation

ggerganov
Copy link
Owner

@ggerganov ggerganov commented Jul 11, 2024

Extend Metal backend to work with BF16 data type.

TODO:

  • GGML_OP_MUL_MAT_ID
  • Flash Attn (in next PR)

@mofosyne mofosyne added the Review Complexity : High Generally require indepth knowledge of LLMs or GPUs label Jul 13, 2024
@robbiemu
Copy link
Contributor

pardon the ignorance,

what does this add bf16 support to using metal?

I see my gpu spinning making imatrices, and with llama-cli on bf16 models.

@ggerganov ggerganov mentioned this pull request Nov 4, 2024
2 tasks
@github-actions github-actions bot added the testing Everything test related label Nov 6, 2024
@ggerganov ggerganov marked this pull request as ready for review November 6, 2024 16:31
@ggerganov ggerganov merged commit 5c333e0 into master Nov 6, 2024
53 checks passed
@ggerganov ggerganov deleted the gg/metal-bf16 branch November 6, 2024 17:53
apicalshark added a commit to apicalshark/llama.cpp that referenced this pull request Nov 7, 2024
* metal : fix minor string leaks (ggml/1004)

* cmake : make it possible linking ggml as external lib (ggml/1003)

* sync : ggml

* CANN: adjust backend registry refactor. (ggerganov#10158)

remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.

* metal : move dequantize templates to beginning of MSL source (#0)

* metal : simplify f16 and f32 dequant kernels (#0)

* cuda : clear error after changing peer access (ggerganov#10153)

* fix build break on arm64 linux (ggerganov#10166)

This fixes the build break from the recent changes
to move the CPU backend to separate files
ggerganov#10144

* server : clarify /slots endpoint, add is_processing (ggerganov#10162)

* server : clarify /slots endpoint, add is_processing

* fix tests

* ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment (ggerganov#10167)

* ggml : fix gelu tables initialization (ggerganov#10172)

* Q6_K AVX improvements (ggerganov#10118)

* q6_k instruction reordering attempt

* better subtract method

* should be theoretically faster

small improvement with shuffle lut, likely because all loads are already done at that stage

* optimize bit fiddling

* handle -32 offset separately. bsums exists for a reason!

* use shift

* Update ggml-quants.c

* have to update ci macos version to 13 as 12 doesnt work now. 13 is still x86

* ggml : fix arch check in bf16_to_fp32 (ggerganov#10164)

* llama : add <|tool_call|> formatting to Granite template (ggerganov#10177)

Branch: GraniteToolCallTemplate

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* metal : add quantized FA support (ggerganov#10149)

* metal : add quantized FA (vec) support

ggml-ci

* metal : add quantized FA (non-vec) support

* metal : fix support check

ggml-ci

* metal : clean-up

* metal : clean-up (cont)

* metal : fix shared memory calc + reduce smem + comments

* metal : float-correctness

* metal : minor [no ci]

* ggml : adjust is_first_call init value (ggerganov#10193)

ggml-ci

* metal : fix from ptr buffer name (ggerganov#10189)

* server : remove hack for extra parallel slot (ggerganov#10187)

ggml-ci

* metal : add BF16 support (ggerganov#8439)

* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
apicalshark added a commit to apicalshark/llama.cpp that referenced this pull request Nov 8, 2024
* Merge PR (#10) (#11) (#13)

Merge

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Bump requests from 2.31.0 to 2.32.2 in the pip group across 1 directory

Bumps the pip group with 1 update in the / directory: [requests](https://github.com/psf/requests).


Updates `requests` from 2.31.0 to 2.32.2
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](psf/requests@v2.31.0...v2.32.2)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>

* Temp (#15)

* metal : fix minor string leaks (ggml/1004)

* cmake : make it possible linking ggml as external lib (ggml/1003)

* sync : ggml

* CANN: adjust backend registry refactor. (ggerganov#10158)

remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.

* metal : move dequantize templates to beginning of MSL source (#0)

* metal : simplify f16 and f32 dequant kernels (#0)

* cuda : clear error after changing peer access (ggerganov#10153)

* fix build break on arm64 linux (ggerganov#10166)

This fixes the build break from the recent changes
to move the CPU backend to separate files
ggerganov#10144

* server : clarify /slots endpoint, add is_processing (ggerganov#10162)

* server : clarify /slots endpoint, add is_processing

* fix tests

* ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment (ggerganov#10167)

* ggml : fix gelu tables initialization (ggerganov#10172)

* Q6_K AVX improvements (ggerganov#10118)

* q6_k instruction reordering attempt

* better subtract method

* should be theoretically faster

small improvement with shuffle lut, likely because all loads are already done at that stage

* optimize bit fiddling

* handle -32 offset separately. bsums exists for a reason!

* use shift

* Update ggml-quants.c

* have to update ci macos version to 13 as 12 doesnt work now. 13 is still x86

* ggml : fix arch check in bf16_to_fp32 (ggerganov#10164)

* llama : add <|tool_call|> formatting to Granite template (ggerganov#10177)

Branch: GraniteToolCallTemplate

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* metal : add quantized FA support (ggerganov#10149)

* metal : add quantized FA (vec) support

ggml-ci

* metal : add quantized FA (non-vec) support

* metal : fix support check

ggml-ci

* metal : clean-up

* metal : clean-up (cont)

* metal : fix shared memory calc + reduce smem + comments

* metal : float-correctness

* metal : minor [no ci]

* ggml : adjust is_first_call init value (ggerganov#10193)

ggml-ci

* metal : fix from ptr buffer name (ggerganov#10189)

* server : remove hack for extra parallel slot (ggerganov#10187)

ggml-ci

* metal : add BF16 support (ggerganov#8439)

* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
apicalshark added a commit to apicalshark/llama.cpp that referenced this pull request Nov 15, 2024
* Master1 (#17)

* Merge PR (#10) (#11) (#13)

Merge

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Bump requests from 2.31.0 to 2.32.2 in the pip group across 1 directory

Bumps the pip group with 1 update in the / directory: [requests](https://github.com/psf/requests).


Updates `requests` from 2.31.0 to 2.32.2
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](psf/requests@v2.31.0...v2.32.2)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>

* Temp (#15)

* metal : fix minor string leaks (ggml/1004)

* cmake : make it possible linking ggml as external lib (ggml/1003)

* sync : ggml

* CANN: adjust backend registry refactor. (ggerganov#10158)

remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.

* metal : move dequantize templates to beginning of MSL source (#0)

* metal : simplify f16 and f32 dequant kernels (#0)

* cuda : clear error after changing peer access (ggerganov#10153)

* fix build break on arm64 linux (ggerganov#10166)

This fixes the build break from the recent changes
to move the CPU backend to separate files
ggerganov#10144

* server : clarify /slots endpoint, add is_processing (ggerganov#10162)

* server : clarify /slots endpoint, add is_processing

* fix tests

* ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment (ggerganov#10167)

* ggml : fix gelu tables initialization (ggerganov#10172)

* Q6_K AVX improvements (ggerganov#10118)

* q6_k instruction reordering attempt

* better subtract method

* should be theoretically faster

small improvement with shuffle lut, likely because all loads are already done at that stage

* optimize bit fiddling

* handle -32 offset separately. bsums exists for a reason!

* use shift

* Update ggml-quants.c

* have to update ci macos version to 13 as 12 doesnt work now. 13 is still x86

* ggml : fix arch check in bf16_to_fp32 (ggerganov#10164)

* llama : add <|tool_call|> formatting to Granite template (ggerganov#10177)

Branch: GraniteToolCallTemplate

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* metal : add quantized FA support (ggerganov#10149)

* metal : add quantized FA (vec) support

ggml-ci

* metal : add quantized FA (non-vec) support

* metal : fix support check

ggml-ci

* metal : clean-up

* metal : clean-up (cont)

* metal : fix shared memory calc + reduce smem + comments

* metal : float-correctness

* metal : minor [no ci]

* ggml : adjust is_first_call init value (ggerganov#10193)

ggml-ci

* metal : fix from ptr buffer name (ggerganov#10189)

* server : remove hack for extra parallel slot (ggerganov#10187)

ggml-ci

* metal : add BF16 support (ggerganov#8439)

* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Rename build.yml to build-ci.yml

* build.yml

* Update build-ci.yml

* Update CMakeLists.txt

* Update CMakeLists.txt

* Update CMakeLists.txt

* Delete ggml/src/vulkan-shaders/CMakeLists.txt

* Update build.yml

* Update build-ci.yml

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 15, 2024
* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support
apicalshark added a commit to apicalshark/llama.cpp that referenced this pull request Nov 16, 2024
* merge (#20)

* Master1 (#17)

* Merge PR (#10) (#11) (#13)

Merge

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Bump requests from 2.31.0 to 2.32.2 in the pip group across 1 directory

Bumps the pip group with 1 update in the / directory: [requests](https://github.com/psf/requests).


Updates `requests` from 2.31.0 to 2.32.2
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](psf/requests@v2.31.0...v2.32.2)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>

* Temp (#15)

* metal : fix minor string leaks (ggml/1004)

* cmake : make it possible linking ggml as external lib (ggml/1003)

* sync : ggml

* CANN: adjust backend registry refactor. (ggerganov#10158)

remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.

* metal : move dequantize templates to beginning of MSL source (#0)

* metal : simplify f16 and f32 dequant kernels (#0)

* cuda : clear error after changing peer access (ggerganov#10153)

* fix build break on arm64 linux (ggerganov#10166)

This fixes the build break from the recent changes
to move the CPU backend to separate files
ggerganov#10144

* server : clarify /slots endpoint, add is_processing (ggerganov#10162)

* server : clarify /slots endpoint, add is_processing

* fix tests

* ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment (ggerganov#10167)

* ggml : fix gelu tables initialization (ggerganov#10172)

* Q6_K AVX improvements (ggerganov#10118)

* q6_k instruction reordering attempt

* better subtract method

* should be theoretically faster

small improvement with shuffle lut, likely because all loads are already done at that stage

* optimize bit fiddling

* handle -32 offset separately. bsums exists for a reason!

* use shift

* Update ggml-quants.c

* have to update ci macos version to 13 as 12 doesnt work now. 13 is still x86

* ggml : fix arch check in bf16_to_fp32 (ggerganov#10164)

* llama : add <|tool_call|> formatting to Granite template (ggerganov#10177)

Branch: GraniteToolCallTemplate

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* metal : add quantized FA support (ggerganov#10149)

* metal : add quantized FA (vec) support

ggml-ci

* metal : add quantized FA (non-vec) support

* metal : fix support check

ggml-ci

* metal : clean-up

* metal : clean-up (cont)

* metal : fix shared memory calc + reduce smem + comments

* metal : float-correctness

* metal : minor [no ci]

* ggml : adjust is_first_call init value (ggerganov#10193)

ggml-ci

* metal : fix from ptr buffer name (ggerganov#10189)

* server : remove hack for extra parallel slot (ggerganov#10187)

ggml-ci

* metal : add BF16 support (ggerganov#8439)

* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Rename build.yml to build-ci.yml

* build.yml

* Update build-ci.yml

* Update CMakeLists.txt

* Update CMakeLists.txt

* Update CMakeLists.txt

* Delete ggml/src/vulkan-shaders/CMakeLists.txt

* Update build.yml

* Update build-ci.yml

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support
apicalshark added a commit to apicalshark/llama.cpp that referenced this pull request Nov 22, 2024
* Merge (#21)

* merge (#20)

* Master1 (#17)

* Merge PR (#10) (#11) (#13)

Merge

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Bump requests from 2.31.0 to 2.32.2 in the pip group across 1 directory

Bumps the pip group with 1 update in the / directory: [requests](https://github.com/psf/requests).


Updates `requests` from 2.31.0 to 2.32.2
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](psf/requests@v2.31.0...v2.32.2)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>

* Temp (#15)

* metal : fix minor string leaks (ggml/1004)

* cmake : make it possible linking ggml as external lib (ggml/1003)

* sync : ggml

* CANN: adjust backend registry refactor. (ggerganov#10158)

remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.

* metal : move dequantize templates to beginning of MSL source (#0)

* metal : simplify f16 and f32 dequant kernels (#0)

* cuda : clear error after changing peer access (ggerganov#10153)

* fix build break on arm64 linux (ggerganov#10166)

This fixes the build break from the recent changes
to move the CPU backend to separate files
ggerganov#10144

* server : clarify /slots endpoint, add is_processing (ggerganov#10162)

* server : clarify /slots endpoint, add is_processing

* fix tests

* ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment (ggerganov#10167)

* ggml : fix gelu tables initialization (ggerganov#10172)

* Q6_K AVX improvements (ggerganov#10118)

* q6_k instruction reordering attempt

* better subtract method

* should be theoretically faster

small improvement with shuffle lut, likely because all loads are already done at that stage

* optimize bit fiddling

* handle -32 offset separately. bsums exists for a reason!

* use shift

* Update ggml-quants.c

* have to update ci macos version to 13 as 12 doesnt work now. 13 is still x86

* ggml : fix arch check in bf16_to_fp32 (ggerganov#10164)

* llama : add <|tool_call|> formatting to Granite template (ggerganov#10177)

Branch: GraniteToolCallTemplate

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* metal : add quantized FA support (ggerganov#10149)

* metal : add quantized FA (vec) support

ggml-ci

* metal : add quantized FA (non-vec) support

* metal : fix support check

ggml-ci

* metal : clean-up

* metal : clean-up (cont)

* metal : fix shared memory calc + reduce smem + comments

* metal : float-correctness

* metal : minor [no ci]

* ggml : adjust is_first_call init value (ggerganov#10193)

ggml-ci

* metal : fix from ptr buffer name (ggerganov#10189)

* server : remove hack for extra parallel slot (ggerganov#10187)

ggml-ci

* metal : add BF16 support (ggerganov#8439)

* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Rename build.yml to build-ci.yml

* build.yml

* Update build-ci.yml

* Update CMakeLists.txt

* Update CMakeLists.txt

* Update CMakeLists.txt

* Delete ggml/src/vulkan-shaders/CMakeLists.txt

* Update build.yml

* Update build-ci.yml

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Update build-ci.yml

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
apicalshark added a commit to apicalshark/llama.cpp that referenced this pull request Dec 1, 2024
* Temp (#23)

* Merge (#21)

* merge (#20)

* Master1 (#17)

* Merge PR (#10) (#11) (#13)

Merge

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* Bump requests from 2.31.0 to 2.32.2 in the pip group across 1 directory

Bumps the pip group with 1 update in the / directory: [requests](https://github.com/psf/requests).


Updates `requests` from 2.31.0 to 2.32.2
- [Release notes](https://github.com/psf/requests/releases)
- [Changelog](https://github.com/psf/requests/blob/main/HISTORY.md)
- [Commits](psf/requests@v2.31.0...v2.32.2)

---
updated-dependencies:
- dependency-name: requests
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>

* Temp (#15)

* metal : fix minor string leaks (ggml/1004)

* cmake : make it possible linking ggml as external lib (ggml/1003)

* sync : ggml

* CANN: adjust backend registry refactor. (ggerganov#10158)

remove buffer->iface.get_name that used in cann as it was removed in backend registry refactor PR.

* metal : move dequantize templates to beginning of MSL source (#0)

* metal : simplify f16 and f32 dequant kernels (#0)

* cuda : clear error after changing peer access (ggerganov#10153)

* fix build break on arm64 linux (ggerganov#10166)

This fixes the build break from the recent changes
to move the CPU backend to separate files
ggerganov#10144

* server : clarify /slots endpoint, add is_processing (ggerganov#10162)

* server : clarify /slots endpoint, add is_processing

* fix tests

* ggml : fix q4xx mat mul, increase ggml_aligned_malloc alignment (ggerganov#10167)

* ggml : fix gelu tables initialization (ggerganov#10172)

* Q6_K AVX improvements (ggerganov#10118)

* q6_k instruction reordering attempt

* better subtract method

* should be theoretically faster

small improvement with shuffle lut, likely because all loads are already done at that stage

* optimize bit fiddling

* handle -32 offset separately. bsums exists for a reason!

* use shift

* Update ggml-quants.c

* have to update ci macos version to 13 as 12 doesnt work now. 13 is still x86

* ggml : fix arch check in bf16_to_fp32 (ggerganov#10164)

* llama : add <|tool_call|> formatting to Granite template (ggerganov#10177)

Branch: GraniteToolCallTemplate

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* metal : add quantized FA support (ggerganov#10149)

* metal : add quantized FA (vec) support

ggml-ci

* metal : add quantized FA (non-vec) support

* metal : fix support check

ggml-ci

* metal : clean-up

* metal : clean-up (cont)

* metal : fix shared memory calc + reduce smem + comments

* metal : float-correctness

* metal : minor [no ci]

* ggml : adjust is_first_call init value (ggerganov#10193)

ggml-ci

* metal : fix from ptr buffer name (ggerganov#10189)

* server : remove hack for extra parallel slot (ggerganov#10187)

ggml-ci

* metal : add BF16 support (ggerganov#8439)

* ggml : add initial BF16 support

ggml-ci

* metal : add mul_mat_id BF16 support

ggml-ci

* metal : check for bfloat support on the Metal device

ggml-ci

* metal : better var names [no ci]

* metal : do not build bfloat kernels when not supported

ggml-ci

* metal : try to fix BF16 support check

ggml-ci

* metal : this should correctly check bfloat support

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Rename build.yml to build-ci.yml

* build.yml

* Update build-ci.yml

* Update CMakeLists.txt

* Update CMakeLists.txt

* Update CMakeLists.txt

* Delete ggml/src/vulkan-shaders/CMakeLists.txt

* Update build.yml

* Update build-ci.yml

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Update build-ci.yml

* Update build-ci.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>

* Bump the pip group across 2 directories with 2 updates (#24)

Updates the requirements on [pillow](https://github.com/python-pillow/Pillow) and [aiohttp](https://github.com/aio-libs/aiohttp) to permit the latest version.

Updates `pillow` to 11.0.0
- [Release notes](https://github.com/python-pillow/Pillow/releases)
- [Changelog](https://github.com/python-pillow/Pillow/blob/main/CHANGES.rst)
- [Commits](python-pillow/Pillow@10.2.0...11.0.0)

Updates `aiohttp` to 3.11.7
- [Release notes](https://github.com/aio-libs/aiohttp/releases)
- [Changelog](https://github.com/aio-libs/aiohttp/blob/master/CHANGES.rst)
- [Commits](aio-libs/aiohttp@v3.9.3...v3.11.7)

---
updated-dependencies:
- dependency-name: pillow
  dependency-type: direct:production
  dependency-group: pip
- dependency-name: aiohttp
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: apicalshark <58538165+apicalshark@users.noreply.github.com>

* Update build-ci.yml

* Update build-ci.yml

* Update build-ci.yml

* Update build-ci.yml

* Update build-ci.yml

* Update build-ci.yml

* Update build-ci.yml

* Update build-ci.yml

* Create docker.yml

* Create python-lint.yml

* Create server.yml

* Update requirements.txt

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Co-authored-by: dennyxbox890 <58538165+dennyxbox890@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Plamen Minev <pacominev@gmail.com>
Co-authored-by: Yuri Khrustalev <ykhrustalev@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
Co-authored-by: snadampal <87143774+snadampal@users.noreply.github.com>
Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
Co-authored-by: Eve <139727413+netrunnereve@users.noreply.github.com>
Co-authored-by: Gabe Goodhart <ghart@us.ibm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Review Complexity : High Generally require indepth knowledge of LLMs or GPUs testing Everything test related
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants